© 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. 6937
    Prev
    Next
    INDEX
    Explanations

    mentions of social or political movements or occupations

    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
    178
    +0.12
    0.5%
    285
    +0.11
    0.5%
    47
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.12
    0.07
    48
    +0.11
    0.08
    85
    +0.10
    0.08
    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.86
    llan
    -0.82
    office
    -0.77
    exempt
    -0.71
    CHAT
    -0.71
    dar
    -0.70
     DIRECT
    -0.70
    INAL
    -0.67
    lda
    -0.67
    ~~~~~~~~
    -0.65
    POSITIVE LOGITS
    iers
    1.16
    icked
    1.07
    iership
    1.01
    yp
    1.00
    isted
    0.97
    aunted
    0.93
    icating
    0.91
    ying
    0.90
    enting
    0.90
    uous
    0.90
    Activations Density 1.542%

    No Known Activations