© 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 EvalsExportsinterp-engineNEWAPI 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. 32279
    Prev
    Next
    INDEX
    Explanations

    words related to education policy and standards

    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
    326
    +0.14
    0.6%
    739
    +0.12
    0.5%
    742
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.20
    326
    +0.12
    0.19
    709
    +0.11
    0.12
    Negative Logits
    downs
    -1.23
    down
    -1.15
    eways
    -0.91
     Osw
    -0.88
    pocket
    -0.88
     Twain
    -0.84
     Colt
    -0.82
     Sands
    -0.81
     Down
    -0.79
    rooms
    -0.79
    POSITIVE LOGITS
    stasy
    1.20
    uador
    1.12
    eger
    0.97
    onut
    0.89
    redits
    0.88
    entric
    0.88
    ¥ŀ
    0.87
    static
    0.86
    risis
    0.85
    pecially
    0.84
    Activations Density 6.846%

    No Known Activations