© 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. 12953
    Prev
    Next
    INDEX
    Explanations

    technical terms related to a specific field or topic, which seems to be about gaming or technology

    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
    203
    +0.19
    0.6%
    298
    +0.15
    0.4%
    436
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.19
    0.18
    325
    +0.15
    0.09
    545
    +0.14
    0.07
    Negative Logits
    iqueness
    -1.30
    ufact
    -1.27
    ensical
    -1.19
     citiz
    -1.13
    hower
    -1.11
    blance
    -1.08
    raped
    -1.01
     specificity
    -0.99
    inness
    -0.93
    aphael
    -0.93
    POSITIVE LOGITS
    imaru
    1.49
    Ń·
    1.22
    tes
    1.13
    velt
    1.11
    thur
    1.11
     XT
    1.05
    eda
    1.00
    ando
    0.96
    charg
    0.96
     Archdemon
    0.95
    Activations Density 5.263%

    No Known Activations