© 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 12288
    9. 8-RES_FS12288-JB
    11. 1371
    Prev
    Next
    INDEX
    Explanations

    abbreviations related to legal and technological terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    447
    +0.19
    0.8%
    729
    +0.11
    0.5%
    564
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    461
    +0.19
    0.06
    594
    +0.11
    0.05
    93
    +0.10
    0.05
    Negative Logits
    Rust
    -0.79
     Mercer
    -0.79
    lett
    -0.68
    rimp
    -0.64
     Riley
    -0.64
    oup
    -0.64
     Schwe
    -0.63
    bern
    -0.63
    Tenn
    -0.63
    Commerce
    -0.63
    POSITIVE LOGITS
     activation
    0.85
     deficiency
    0.84
     inhibitors
    0.83
     installations
    0.81
     holders
    0.81
     proponents
    0.78
     activ
    0.77
     status
    0.77
     technology
    0.77
     tokens
    0.76
    Activations Density 0.435%

    No Known Activations