© 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. 2824
    Prev
    Next
    INDEX
    Explanations

    phrases related to different "-ism" concepts, such as nationalism, socialism, individualism, and more

    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
    288
    +0.22
    0.9%
    97
    +0.16
    0.7%
    267
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.22
    0.08
    709
    +0.16
    0.05
    613
    +0.16
    0.05
    Negative Logits
    VEN
    -0.87
    vag
    -0.87
    STON
    -0.82
    ergy
    -0.80
    VID
    -0.78
    JUST
    -0.75
    thening
    -0.74
    bred
    -0.74
    BOOK
    -0.74
    âĸ¬âĸ¬
    -0.73
    POSITIVE LOGITS
    yip
    1.16
    atics
    1.15
    atic
    1.00
    obiles
    0.94
    atism
    0.94
    ophical
    0.93
    ocrat
    0.93
    uffs
    0.89
    ocene
    0.88
    edia
    0.88
    Activations Density 1.269%

    No Known Activations