© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 12649
    Prev
    Next
    INDEX
    Explanations

    references to sources, figures, or external documents for further information, as well as listings and charts for data analysis

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.15
    0.7%
    604
    +0.12
    0.6%
    61
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    61
    +0.15
    0.04
    604
    +0.12
    0.03
    475
    +0.12
    0.03
    Negative Logits
    ersive
    -0.73
     Mahjong
    -0.68
    owered
    -0.64
    ciplinary
    -0.64
    ococ
    -0.61
     imperson
    -0.61
    affle
    -0.61
    intend
    -0.60
    obook
    -0.59
    alties
    -0.59
    POSITIVE LOGITS
     ).
    1.37
    ).
    1.35
    )."
    1.33
    )).
    1.31
    .).
    1.23
    ]).
    1.21
    ?).
    1.20
     .)
    1.13
    !).
    1.11
    )—
    1.10
    Activations Density 0.117%

    No Known Activations