© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 36784
    Prev
    Next
    INDEX
    Explanations

    terms related to different orientations and classifications, such as sexual orientation, race, and religious orientation

    oai_token-act-pair · gpt-3.5-turbo

    Sexual orientations, gender identities, and the words "orientation", "Orient", "sexual attraction", and related concepts and examples of such things.

    Explanation Uploaded by User
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.12
    0.7%
    575
    +0.10
    0.6%
    642
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.12
    0.16
    288
    +0.10
    0.19
    724
    +0.10
    0.13
    Negative Logits
    soDeliveryDate
    -0.74
    asp
    -0.57
    otte
    -0.55
    enegger
    -0.53
    winter
    -0.52
    oval
    -0.52
    prus
    -0.50
    inventoryQuantity
    -0.50
    olly
    -0.50
    女
    -0.49
    POSITIVE LOGITS
    eering
    0.89
     orientation
    0.74
    xual
    0.62
    ¥µ
    0.59
     illum
    0.58
    uality
    0.58
    ï¸
    0.57
     allegiance
    0.54
    anship
    0.54
     versa
    0.53
    Activations Density 5.529%

    No Known Activations