© 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 49152
    9. 8-RES_FS49152-JB
    11. 37233
    Prev
    Next
    INDEX
    Explanations

    phrases indicating location or contextual positioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    136
    +0.11
    0.5%
    530
    +0.11
    0.5%
    626
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    553
    +0.11
    0.02
    471
    +0.11
    0.02
    534
    +0.10
    0.01
    Negative Logits
     Entered
    -0.78
     Growth
    -0.74
    bur
    -0.72
    ges
    -0.69
     Components
    -0.68
    ctors
    -0.67
    icter
    -0.66
    talk
    -0.66
    gerald
    -0.64
    overed
    -0.63
    POSITIVE LOGITS
     sparing
    0.85
     whim
    0.77
     solo
    0.74
     shame
    0.73
    pless
    0.73
     yourself
    0.72
     earnest
    0.72
     anyway
    0.72
     legally
    0.71
     cheaply
    0.71
    Activations Density 0.121%

    No Known Activations