© 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. 18856
    Prev
    Next
    INDEX
    Explanations

    phrases related to unity, community, and collaboration

    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
    578
    +0.12
    0.5%
    412
    +0.11
    0.5%
    455
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.12
    0.05
    393
    +0.11
    0.06
    284
    +0.11
    0.05
    Negative Logits
    zan
    -0.90
    mate
    -0.76
    mates
    -0.76
    gypt
    -0.75
    Lago
    -0.74
    ļéĨĴ
    -0.74
    ģĸ
    -0.72
    thood
    -0.71
    utch
    -0.71
    BRE
    -0.70
    POSITIVE LOGITS
     intric
    0.91
     complexities
    0.84
     majesty
    0.82
    iest
    0.81
     aroma
    0.80
     totality
    0.79
     virtues
    0.78
     atmosphere
    0.76
     vibe
    0.76
     accompanying
    0.75
    Activations Density 0.248%

    No Known Activations