© 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. 12607
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terms and court cases

    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
    +0.14
    0.6%
    125
    +0.10
    0.4%
    298
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.14
    0.15
    125
    +0.10
    0.10
    271
    +0.09
    0.08
    Negative Logits
    arlane
    -0.69
    olicited
    -0.66
    called
    -0.64
    iew
    -0.62
    gemony
    -0.62
    aa
    -0.59
    idth
    -0.59
    ipe
    -0.58
    tein
    -0.58
    obal
    -0.58
    POSITIVE LOGITS
     psychiat
    0.71
     hinges
    0.68
    ãĢĤ
    0.66
    .–
    0.66
     Hendricks
    0.62
    .>>
    0.62
    .(
    0.62
     è£ıè
    0.62
    intendent
    0.61
    aneously
    0.61
    Activations Density 3.279%

    No Known Activations