© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1650
    Prev
    Next
    INDEX
    Explanations

    references to political terms and limits

    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
    715
    +0.07
    0.6%
    35
    +0.07
    0.6%
    195
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    715
    +0.07
    0.04
    666
    +0.07
    0.03
    198
    +0.07
    0.03
    Negative Logits
    ãĤ´ãĥ³
    -0.50
    âķIJ
    -0.42
    oute
    -0.42
    lement
    -0.41
     Ney
    -0.41
     Juda
    -0.41
    erie
    -0.40
     disparate
    -0.39
    yre
    -0.37
    chy
    -0.37
    POSITIVE LOGITS
    mits
    0.56
    acity
    0.54
    abilities
    0.51
    mate
    0.50
    marks
    0.47
    sworth
    0.46
    acious
    0.46
    ilk
    0.44
    oshenko
    0.44
    ability
    0.44
    Activations Density 0.349%

    No Known Activations