© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8819
    Prev
    Next
    INDEX
    Explanations

    specific names and concepts related to political and social issues

    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
    165
    +0.17
    0.5%
    595
    +0.15
    0.4%
    298
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.17
    0.08
    326
    +0.15
    0.13
    232
    +0.14
    0.06
    Negative Logits
    ĸļ
    -1.41
     pronounced
    -1.13
    ayn
    -0.99
     consideration
    -0.95
    kefeller
    -0.91
     slump
    -0.91
     Cameron
    -0.91
    Ö¼
    -0.91
     whis
    -0.90
    enegger
    -0.88
    POSITIVE LOGITS
    ucket
    1.25
    ãĥ´ãĤ¡
    1.10
    ioned
    1.08
    ohyd
    1.05
    ocene
    1.04
    hemy
    1.02
    otta
    1.02
    tarians
    1.00
    aneous
    1.00
    é¾įåĸļ士
    1.00
    Activations Density 3.039%

    No Known Activations