© 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. 1692
    Prev
    Next
    INDEX
    Explanations

    technical specifications and features of a device or product

    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
    410
    +0.10
    0.5%
    693
    +0.10
    0.5%
    409
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    643
    +0.10
    0.06
    455
    +0.10
    0.07
    745
    +0.09
    -0.00
    Negative Logits
    kens
    -0.74
    ESE
    -0.71
    saf
    -0.69
     reinstated
    -0.69
    strength
    -0.68
    united
    -0.67
     restored
    -0.66
     largeDownload
    -0.66
    orld
    -0.65
    Newsletter
    -0.65
    POSITIVE LOGITS
     wasteful
    1.07
     distractions
    1.03
     unnecessary
    1.02
     reliance
    1.02
     waste
    0.99
     undue
    0.97
     clutter
    0.93
     excessive
    0.92
     overly
    0.91
     wasting
    0.91
    Activations Density 0.593%

    No Known Activations