© 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. 37308
    Prev
    Next
    INDEX
    Explanations

    mentions of Twitter handles

    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
    314
    +0.15
    0.7%
    326
    +0.11
    0.5%
    267
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    445
    +0.15
    0.02
    371
    +0.11
    0.02
    627
    +0.10
    0.02
    Negative Logits
    emonium
    -0.73
     circulation
    -0.72
     assum
    -0.71
     Dise
    -0.68
     aspir
    -0.65
     deflation
    -0.64
     liner
    -0.64
     orche
    -0.63
     reconc
    -0.62
     shuff
    -0.62
    POSITIVE LOGITS
    #$
    1.47
    realDonaldTrump
    1.41
    @@@@@@@@
    1.11
    gmail
    1.07
    Home
    0.92
    home
    0.90
    TPS
    0.87
    INC
    0.86
    aic
    0.85
    NO
    0.85
    Activations Density 0.012%

    No Known Activations