© 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. 31764
    Prev
    Next
    INDEX
    Explanations

    words related to violence against women

    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
    +0.25
    1.2%
    383
    +0.15
    0.7%
    323
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    383
    +0.25
    0.10
    575
    +0.15
    0.13
    323
    +0.10
    0.09
    Negative Logits
    PDATE
    -0.80
    aeda
    -0.79
    rehend
    -0.77
    CAST
    -0.68
    fusc
    -0.66
    odcast
    -0.65
    rawdownloadcloneembedreportprint
    -0.65
    aution
    -0.64
    arily
    -0.64
    utherford
    -0.64
    POSITIVE LOGITS
     Scouts
    0.94
    folk
    0.87
     girls
    0.82
     panties
    0.80
    girl
    0.79
    ish
    0.78
    girls
    0.77
    hood
    0.73
    pher
    0.71
     Louise
    0.70
    Activations Density 7.661%

    No Known Activations