© 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. 26598
    Prev
    Next
    INDEX
    Explanations

    references to pathways or roadways

    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
    481
    +0.12
    0.6%
    435
    +0.10
    0.5%
    211
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    325
    +0.12
    0.02
    24
    +0.10
    0.01
    435
    +0.10
    0.01
    Negative Logits
    anguage
    -0.84
    ividual
    -0.79
    icio
    -0.79
    munition
    -0.74
    uster
    -0.74
    owship
    -0.69
    itatively
    -0.68
    kus
    -0.66
    encer
    -0.65
    grave
    -0.65
    POSITIVE LOGITS
    ways
    1.04
    finding
    1.00
    way
    0.97
    fare
    0.91
    bill
    0.81
    chairs
    0.80
     junction
    0.78
     entrances
    0.78
     closures
    0.77
    route
    0.76
    Activations Density 0.018%

    No Known Activations