© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 18814
    Prev
    Next
    INDEX
    Explanations

    time-related references, especially in the context of narratives or descriptions

    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
    231
    +0.09
    0.4%
    280
    +0.09
    0.4%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    633
    +0.09
    0.02
    650
    +0.09
    0.02
    280
    +0.09
    0.02
    Negative Logits
     Flavoring
    -0.75
     Cosponsors
    -0.75
    æĦ
    -0.65
    sectional
    -0.64
     Features
    -0.64
    ector
    -0.63
    fml
    -0.63
    erville
    -0.62
     Supports
    -0.62
    Platform
    -0.60
    POSITIVE LOGITS
    consuming
    0.98
     lapse
    0.90
     continuum
    0.86
    apsed
    0.82
     elapsed
    0.79
    hon
    0.77
     spent
    0.75
    travel
    0.73
     wasted
    0.71
    nown
    0.71
    Activations Density 0.114%

    No Known Activations