© 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. 6294
    Prev
    Next
    INDEX
    Explanations

    mentions of private matters or individuals in a potentially controversial context

    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
    656
    +0.13
    0.6%
    302
    +0.13
    0.6%
    370
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    656
    +0.13
    0.04
    302
    +0.13
    0.04
    80
    +0.11
    0.03
    Negative Logits
     GOODMAN
    -0.76
    rers
    -0.74
    xual
    -0.73
    awa
    -0.73
    DAY
    -0.70
    wolves
    -0.69
    annis
    -0.69
    rer
    -0.68
    addons
    -0.68
    amaz
    -0.67
    POSITIVE LOGITS
     sector
    1.10
     equity
    0.92
     Sector
    0.82
     affairs
    0.80
     rented
    0.77
    sector
    0.77
     property
    0.76
     ownership
    0.74
     investigator
    0.74
    ised
    0.73
    Activations Density 0.026%

    No Known Activations