© 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 Local
    9. 6-RES_SCL-AJT
    11. 33581
    Prev
    Next
    INDEX
    Explanations

    phrases related to military and political events

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    756
    +0.14
    0.7%
    447
    +0.13
    0.6%
    343
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.14
    0.09
    288
    +0.13
    0.18
    659
    +0.10
    0.09
    Negative Logits
    rored
    -0.73
    lot
    -0.71
    é¾įå¥ij士
    -0.69
    Ö¼
    -0.66
    sburgh
    -0.66
    owship
    -0.66
    ilater
    -0.63
    ibly
    -0.62
    ROR
    -0.61
     mathemat
    -0.61
    POSITIVE LOGITS
    ÄŁ
    0.98
    qua
    0.98
    ji
    0.96
    zzi
    0.94
    gha
    0.87
    pper
    0.85
    ichi
    0.82
    jin
    0.82
    opsy
    0.81
    zu
    0.80
    Activations Density 6.181%

    No Known Activations