© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 37231
    Prev
    Next
    INDEX
    Explanations

    a variety of forms of the verb "to be" with a focus on their inflected versions

    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
    695
    +0.13
    0.6%
    42
    +0.10
    0.4%
    506
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    670
    +0.13
    0.01
    42
    +0.10
    0.01
    598
    +0.09
    0.01
    Negative Logits
    etheless
    -0.99
    loo
    -0.84
    elaide
    -0.76
    inness
    -0.75
    agher
    -0.74
    arians
    -0.72
    bley
    -0.71
    ilan
    -0.70
    wcs
    -0.70
    berra
    -0.70
    POSITIVE LOGITS
     Chart
    0.73
    itect
    0.68
     Leopard
    0.67
    ouver
    0.67
    ORED
    0.66
     percentages
    0.64
     bould
    0.63
     proportion
    0.62
    ULT
    0.62
    itized
    0.62
    Activations Density 0.018%

    No Known Activations