© 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 24576
    9. 8-RES_FS24576-JB
    11. 23857
    Prev
    Next
    INDEX
    Explanations

    prominent individuals and their roles or actions related to leadership or notable situations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    +0.29
    1.4%
    15
    +0.10
    0.5%
    134
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.29
    0.04
    346
    +0.10
    0.04
    232
    +0.10
    0.04
    Negative Logits
    lihood
    -0.82
    CONCLUS
    -0.74
    RESULTS
    -0.73
    thumbnails
    -0.70
    )."
    -0.67
    ilial
    -0.67
    />
    -0.66
    selves
    -0.65
    >.
    -0.64
    vg
    -0.64
    POSITIVE LOGITS
     frontman
    0.65
    reetings
    0.63
     Hockey
    0.59
     whisky
    0.59
     baseman
    0.57
     hockey
    0.56
     awoke
    0.55
     defenseman
    0.55
    ONDON
    0.54
    umbai
    0.54
    Activations Density 0.224%

    No Known Activations