© 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. 687
    Prev
    Next
    INDEX
    Explanations

    conjunctions indicating causation

    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
    240
    +0.12
    0.5%
    214
    +0.12
    0.5%
    468
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    240
    +0.12
    0.04
    468
    +0.12
    0.04
    214
    +0.11
    0.03
    Negative Logits
     nic
    -0.64
    gie
    -0.63
     Neigh
    -0.61
    NF
    -0.59
     Federal
    -0.57
    WN
    -0.57
     burg
    -0.57
    ropolitan
    -0.56
     Alpine
    -0.56
     Bastard
    -0.55
    POSITIVE LOGITS
     forth
    1.28
    bered
    1.15
    oner
    1.11
    apy
    1.02
    oths
    1.00
    othe
    0.95
    forth
    0.95
    ooo
    0.92
     far
    0.89
    oooo
    0.87
    Activations Density 0.088%

    No Known Activations