© 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 3072
    9. 8-RES_FS3072-JB
    11. 2977
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data analysis and database research

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    741
    +0.09
    0.4%
    65
    +0.08
    0.4%
    229
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.09
    0.09
    73
    +0.08
    0.09
    765
    +0.08
    0.09
    Negative Logits
    ");
    -0.71
    tsy
    -0.65
    ").
    -0.61
    ');
    -0.60
    "/>
    -0.58
    inqu
    -0.56
    vale
    -0.56
    igmatic
    -0.55
    nih
    -0.55
    "...
    -0.55
    POSITIVE LOGITS
     meanwhile
    1.43
     however
    1.27
     moreover
    1.15
     alas
    1.02
     unsurprisingly
    0.97
     huh
    0.91
     incidentally
    0.91
     along
    0.89
     coupled
    0.88
     therefore
    0.86
    Activations Density 1.121%

    No Known Activations