© 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 EvalsExportsAPI 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 12827
    Prev
    Next
    INDEX
    Explanations

    descriptions or examples of social issues related to discrimination or mistreatment

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    393
    +0.17
    0.6%
    614
    +0.13
    0.5%
    317
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.17
    0.04
    688
    +0.13
    0.05
    236
    +0.12
    0.06
    Negative Logits
     Tent
    -0.77
     Papua
    -0.75
    axies
    -0.74
     Oxy
    -0.72
     Amph
    -0.71
     crabs
    -0.71
     Bigfoot
    -0.70
    enko
    -0.70
     Kavanaugh
    -0.69
     Expedition
    -0.69
    POSITIVE LOGITS
    Else
    1.39
    nam
    1.11
     equivalent
    1.00
    abouts
    0.97
     versa
    0.97
    depending
    0.93
     combination
    0.91
    chard
    0.88
    ught
    0.88
    acle
    0.88
    Activations Density 1.229%

    No Known Activations