© 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. 36106
    Prev
    Next
    INDEX
    Explanations

    emotional and descriptive language related to visual observations, interactions, and feelings

    oai_token-act-pair · gpt-3.5-turbo
    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
    +0.21
    1.0%
    326
    +0.18
    0.8%
    407
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.21
    0.23
    274
    +0.18
    0.11
    23
    +0.12
    0.12
    Negative Logits
    inventoryQuantity
    -0.86
    interstitial
    -0.74
    rosse
    -0.72
    notes
    -0.72
    ctr
    -0.70
    ERN
    -0.68
    icult
    -0.68
    cephal
    -0.66
    usual
    -0.64
    icum
    -0.64
    POSITIVE LOGITS
     gaze
    0.97
     stare
    0.97
     stares
    0.96
     dag
    0.94
     staring
    0.92
    creen
    0.87
     blank
    0.86
     stared
    0.79
    «
    0.75
     unfocused
    0.74
    Activations Density 9.217%

    No Known Activations