© 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. 37341
    Prev
    Next
    INDEX
    Explanations

    scores and statistics related to sporting events

    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
    447
    +0.14
    0.6%
    481
    +0.12
    0.5%
    500
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    281
    +0.14
    0.03
    640
    +0.12
    0.05
    6
    +0.11
    0.04
    Negative Logits
    ickr
    -0.72
     ank
    -0.72
     welf
    -0.69
    ©¶æ¥µ
    -0.68
     projects
    -0.68
     handy
    -0.68
     consultancy
    -0.67
     broch
    -0.67
    leeve
    -0.67
    ãģķ
    -0.67
    POSITIVE LOGITS
     winner
    1.02
    Winner
    1.00
     Showdown
    0.99
     Winners
    0.98
     Winner
    0.97
     rematch
    0.96
     contestants
    0.94
     duel
    0.94
    winner
    0.93
     Finals
    0.93
    Activations Density 0.284%

    No Known Activations