© 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 3072
    9. 8-RES_FS3072-JB
    11. 2985
    Prev
    Next
    INDEX
    Explanations

    information regarding birth and marriage events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    414
    +0.12
    0.5%
    218
    +0.10
    0.4%
    557
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    414
    +0.12
    0.04
    132
    +0.10
    0.04
    545
    +0.10
    0.04
    Negative Logits
    phis
    -0.81
    erguson
    -0.73
    abulary
    -0.73
    awaru
    -0.69
    utical
    -0.67
    uyomi
    -0.65
    phasis
    -0.65
    vernment
    -0.65
    dfx
    -0.64
    bars
    -0.64
    POSITIVE LOGITS
    emis
    0.85
    stellar
    0.78
    onso
    0.77
    days
    0.75
    nings
    0.72
    iny
    0.70
    lings
    0.70
    born
    0.68
    rates
    0.67
     anew
    0.66
    Activations Density 0.550%

    No Known Activations