© 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. 9378
    Prev
    Next
    INDEX
    Explanations

    sports achievements and titles in various leagues and tournaments

    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
    241
    +0.14
    0.6%
    711
    +0.10
    0.5%
    505
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.14
    0.04
    651
    +0.10
    0.05
    540
    +0.10
    0.05
    Negative Logits
     specificity
    -0.81
    effects
    -0.71
    forums
    -0.67
    hor
    -0.65
     consultations
    -0.65
     consultation
    -0.63
    animate
    -0.63
    ãĥ¤
    -0.63
     directions
    -0.62
     hypers
    -0.61
    POSITIVE LOGITS
     consecut
    0.92
     twice
    0.84
     apiece
    0.82
     despite
    0.77
     alongside
    0.77
    ommel
    0.76
    ģĸ
    0.74
     before
    0.74
     during
    0.73
     stint
    0.69
    Activations Density 0.194%

    No Known Activations