© 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. 18895
    Prev
    Next
    INDEX
    Explanations

    news articles related to politics, economics, and crime

    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
    567
    +0.13
    0.6%
    69
    +0.12
    0.6%
    481
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.07
    567
    +0.12
    0.03
    189
    +0.12
    0.03
    Negative Logits
    Thumbnail
    -0.74
    Synopsis
    -0.71
     Nanto
    -0.70
     toile
    -0.65
    andise
    -0.60
    soever
    -0.59
     colle
    -0.57
    OSH
    -0.56
     Recover
    -0.56
     Petr
    -0.55
    POSITIVE LOGITS
     existed
    0.90
     exists
    0.87
     could
    0.81
     hadn
    0.79
     shouldn
    0.77
     should
    0.76
     wouldn
    0.75
     wasn
    0.74
    could
    0.74
     deserved
    0.74
    Activations Density 0.567%

    No Known Activations