© 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. 9234
    Prev
    Next
    INDEX
    Explanations

    references to specific characters or people named "Doc" in the text

    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
    688
    +0.10
    0.5%
    167
    +0.09
    0.4%
    651
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    628
    +0.10
    0.01
    291
    +0.09
    0.01
    688
    +0.09
    0.01
    Negative Logits
     Admir
    -0.75
    places
    -0.71
     Rivals
    -0.63
    mare
    -0.62
     parting
    -0.60
     advis
    -0.60
    boarding
    -0.60
     Royale
    -0.60
    Reloaded
    -0.59
     nav
    -0.59
    POSITIVE LOGITS
    herty
    1.31
    uments
    1.22
    iencies
    1.03
    ents
    1.00
    ilt
    0.96
    ual
    0.94
    ually
    0.94
    umen
    0.88
    ilic
    0.85
    imen
    0.85
    Activations Density 0.024%

    No Known Activations