© 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. 6770
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals named Scott

    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
    683
    +0.17
    0.5%
    346
    +0.16
    0.5%
    232
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.17
    0.07
    288
    +0.16
    0.10
    346
    +0.15
    0.07
    Negative Logits
    ĵĺ
    -1.17
    senal
    -1.06
    chid
    -1.05
    mediate
    -1.03
    pread
    -1.03
    ĺħ
    -1.01
    FER
    -1.00
    FY
    -0.98
    ĪĴ
    -0.96
    ¥µ
    -0.96
    POSITIVE LOGITS
    ards
    1.37
     Morrison
    1.37
    inelli
    1.37
     Pilgrim
    1.36
    inson
    1.35
     Walker
    1.29
    oken
    1.25
    ocks
    1.23
    rade
    1.23
     Olson
    1.21
    Activations Density 1.557%

    No Known Activations