© 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. 1451
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating strong emotions or descriptions

    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
    102
    +0.15
    0.7%
    55
    +0.12
    0.6%
    718
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.15
    0.10
    55
    +0.12
    0.09
    441
    +0.11
    0.07
    Negative Logits
     Flavoring
    -0.94
    idth
    -0.82
    ership
    -0.81
    ortmund
    -0.79
    plings
    -0.77
     Deaths
    -0.76
    rises
    -0.76
    votes
    -0.73
    ãĤº
    -0.73
    enaries
    -0.73
    POSITIVE LOGITS
     interesting
    1.16
     unlikely
    1.11
     fascinating
    1.09
     important
    1.09
     easy
    1.08
     exciting
    1.08
     difficult
    1.06
     reliant
    1.05
     frustrating
    1.05
     obvious
    1.04
    Activations Density 0.321%

    No Known Activations