© 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. 2762
    Prev
    Next
    INDEX
    Explanations

    sections of code where certain specific actions are being performed, such as filtering, removing, or inserting elements

    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
    +0.18
    0.6%
    48
    +0.13
    0.5%
    160
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    645
    +0.18
    0.04
    160
    +0.13
    0.04
    205
    +0.13
    0.04
    Negative Logits
     ransom
    -0.91
     unprepared
    -0.88
     improvis
    -0.86
     smugg
    -0.86
    âĢij
    -0.85
    rawdownloadcloneembedreportprint
    -0.84
     estab
    -0.83
     intimid
    -0.83
     handc
    -0.82
     Burnett
    -0.82
    POSITIVE LOGITS
    *)
    1.40
    ...)
    1.38
    SourceFile
    1.33
    function
    1.20
    src
    1.18
    https
    1.16
    partial
    1.14
    BOOK
    1.14
    ())
    1.13
    ?)
    1.12
    Activations Density 0.231%

    No Known Activations