© 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. 37163
    Prev
    Next
    INDEX
    Explanations

    references to low-cost options or products

    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
    238
    +0.14
    0.6%
    496
    +0.12
    0.6%
    669
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.14
    0.04
    357
    +0.12
    0.03
    495
    +0.10
    0.03
    Negative Logits
    tnc
    -0.90
    andise
    -0.85
     Ashe
    -0.71
    ADRA
    -0.71
    itutional
    -0.64
     Chaser
    -0.64
    ulpt
    -0.63
    ONSORED
    -0.62
    andum
    -0.62
     Pengu
    -0.62
    POSITIVE LOGITS
    ered
    0.86
     altitude
    0.85
    ball
    0.85
    enthal
    0.85
    est
    0.83
     hanging
    0.82
     (<
    0.81
    brow
    0.81
     pitched
    0.80
     enough
    0.78
    Activations Density 0.027%

    No Known Activations