© 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. 19846
    Prev
    Next
    INDEX
    Explanations

    dates in text mentioning years with high activation values

    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
    146
    +0.12
    0.6%
    530
    +0.10
    0.5%
    518
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.12
    0.04
    530
    +0.10
    0.04
    185
    +0.10
    0.04
    Negative Logits
     shenan
    -0.73
     mism
    -0.64
     exploits
    -0.64
    semb
    -0.63
     multic
    -0.62
     smugglers
    -0.62
     unpredictable
    -0.61
    icons
    -0.61
    iaz
    -0.60
    onite
    -0.60
    POSITIVE LOGITS
     UTC
    0.83
     RELEASE
    0.82
     ·
    0.76
     08
    0.73
     Highest
    0.72
     07
    0.69
    Reviewed
    0.68
     Posted
    0.68
     Updated
    0.67
     Became
    0.65
    Activations Density 0.052%

    No Known Activations