© 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. 633
    Prev
    Next
    INDEX
    Explanations

    alphanumeric sequences and programming-related 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
    87
    +0.16
    0.8%
    756
    +0.14
    0.7%
    546
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.16
    -0.02
    570
    +0.14
    0.03
    351
    +0.09
    0.04
    Negative Logits
    ©¶æ
    -0.64
     acron
    -0.62
     Architects
    -0.58
     )]
    -0.57
    thodox
    -0.57
     lately
    -0.57
    emouth
    -0.56
     collaborations
    -0.52
     Malaysia
    -0.52
     Spr
    -0.52
    POSITIVE LOGITS
     automatically
    0.88
     instantly
    0.78
     corresponding
    0.75
     immediately
    0.74
     whichever
    0.72
    mediately
    0.71
     magically
    0.71
     accordingly
    0.70
     downstream
    0.69
     indistinguishable
    0.67
    Activations Density 1.626%

    No Known Activations