© 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. 31973
    Prev
    Next
    INDEX
    Explanations

    adjectives describing something as extraordinary or uncommon in a negative context

    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
    +0.14
    0.9%
    288
    +0.07
    0.5%
    400
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.14
    0.18
    479
    +0.07
    0.01
    442
    +0.07
    0.07
    Negative Logits
    ather
    -0.53
    tein
    -0.48
    yard
    -0.46
    azy
    -0.45
    ippi
    -0.45
    burn
    -0.45
    agra
    -0.45
    ena
    -0.45
    unk
    -0.44
    uffed
    -0.43
    POSITIVE LOGITS
     unprecedented
    0.58
    REAM
    0.54
    judicial
    0.52
    LY
    0.52
     unheard
    0.51
    aneously
    0.51
    wcs
    0.51
     unanim
    0.50
    ZI
    0.50
    itarian
    0.48
    Activations Density 10.404%

    No Known Activations