© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 9885
    Prev
    Next
    INDEX
    Explanations

    details related to a crime incident and legal proceedings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    373
    +0.57
    3.5%
    756
    +0.25
    1.6%
    570
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.57
    -0.03
    373
    +0.25
    -0.11
    570
    +0.07
    0.00
    Negative Logits
     Originally
    -0.52
    htaking
    -0.39
    DragonMagazine
    -0.38
    Picture
    -0.38
     Canaver
    -0.38
    natureconservancy
    -0.36
     Defendants
    -0.36
    reetings
    -0.36
    odcast
    -0.36
     Podcast
    -0.36
    POSITIVE LOGITS
    .).
    0.80
    ).
    0.73
    ).[
    0.71
    )).
    0.69
    }.
    0.68
    %).
    0.67
    )."
    0.66
    ]."
    0.66
    %.
    0.62
    !).
    0.60
    Activations Density 3.990%

    No Known Activations