© 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 49152
    9. 8-RES_FS49152-JB
    11. 41697
    Prev
    Next
    INDEX
    Explanations

    commas and certain punctuation marks in the text

    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
    226
    +0.10
    0.4%
    720
    +0.09
    0.4%
    67
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.10
    0.03
    297
    +0.09
    0.02
    371
    +0.09
    0.02
    Negative Logits
    Angelo
    -0.73
    Ī
    -0.70
    Availability
    -0.68
    gery
    -0.67
     seizures
    -0.66
    Output
    -0.65
     transmissions
    -0.65
     currents
    -0.65
    ¬
    -0.64
    riages
    -0.62
    POSITIVE LOGITS
     dear
    1.19
     sir
    1.18
     gentlemen
    0.89
     reader
    0.88
     please
    0.77
     personally
    0.74
     mate
    0.73
     Reader
    0.73
     whoever
    0.73
     PLEASE
    0.70
    Activations Density 0.067%

    No Known Activations