Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 41557
    Prev
    Next
    INDEX
    Explanations

    references to specific days of the week, particularly Sundays

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    151
    +0.14
    0.6%
    430
    +0.13
    0.6%
    279
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.14
    0.05
    279
    +0.13
    0.04
    151
    +0.12
    0.04
    Negative Logits
     Journals
    -0.94
    itarian
    -0.77
    enegger
    -0.74
    ipation
    -0.74
    estern
    -0.72
    chwitz
    -0.70
    CHQ
    -0.69
    aughs
    -0.69
    anian
    -0.69
    ancial
    -0.68
    POSITIVE LOGITS
     afternoon
    1.35
     night
    1.23
     evening
    1.10
     morning
    1.08
     Night
    1.05
     Stadium
    0.99
     scrimmage
    0.98
     halftime
    0.98
     matchup
    0.98
     rematch
    0.93
    Activations Density 0.062%

    No Known Activations