© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 10739
    Prev
    Next
    INDEX
    Explanations

    information related to publications and articles

    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
    640
    +0.31
    1.5%
    266
    +0.19
    0.9%
    754
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.31
    0.60
    480
    +0.19
    -0.04
    64
    +0.09
    -0.32
    Negative Logits
    EStream
    -0.67
    emort
    -0.67
    iterranean
    -0.63
    ãĥĦ
    -0.63
    mberg
    -0.62
    ignty
    -0.62
    regation
    -0.61
    cence
    -0.60
    umni
    -0.60
    izabeth
    -0.60
    POSITIVE LOGITS
    Guard
    0.80
    ccording
    0.78
    haw
    0.73
    Posted
    0.73
    lines
    0.68
    license
    0.64
    PORT
    0.63
    LOS
    0.63
    CLUS
    0.63
    talk
    0.62
    Activations Density 25.865%

    No Known Activations