© 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. 31493
    Prev
    Next
    INDEX
    Explanations

    gender-related words and phrases, especially focusing on the roles of women in different contexts

    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
    +0.15
    0.7%
    57
    +0.10
    0.5%
    60
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.26
    57
    +0.10
    0.09
    48
    +0.10
    0.10
    Negative Logits
    ysis
    -0.82
    cold
    -0.61
    ground
    -0.61
    Factory
    -0.60
    Dispatch
    -0.58
    enium
    -0.58
    olin
    -0.58
    Package
    -0.58
    illes
    -0.58
    stals
    -0.58
    POSITIVE LOGITS
     outnumbered
    0.68
    volent
    0.65
     supremacist
    0.64
     separatist
    0.63
     slurs
    0.62
     immigrant
    0.62
     slur
    0.61
     affili
    0.61
     stereotyp
    0.61
     bias
    0.61
    Activations Density 13.779%

    No Known Activations