© 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. 37248
    Prev
    Next
    INDEX
    Explanations

    questions or phrases that start with "how."

    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
    195
    +0.12
    0.5%
    236
    +0.11
    0.5%
    101
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    236
    +0.12
    0.05
    263
    +0.11
    0.03
    60
    +0.11
    0.03
    Negative Logits
    ãģĮ
    -0.75
    ãĥĩãĤ£
    -0.71
    åij
    -0.69
    oubted
    -0.69
    topic
    -0.68
    esides
    -0.67
    formance
    -0.67
    izu
    -0.65
    76561
    -0.65
    achelor
    -0.64
    POSITIVE LOGITS
    ls
    0.77
     interconnected
    0.74
     pervasive
    0.74
     prevalent
    0.74
     differently
    0.70
    beit
    0.69
     closely
    0.69
     much
    0.69
     intertwined
    0.68
    agy
    0.66
    Activations Density 0.051%

    No Known Activations