© 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. 37267
    Prev
    Next
    INDEX
    Explanations

    quantitative data related to financial figures and economic statistics

    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
    495
    +0.12
    0.5%
    520
    +0.10
    0.4%
    685
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    495
    +0.12
    0.05
    162
    +0.10
    0.04
    165
    +0.10
    0.04
    Negative Logits
    onga
    -0.71
     Jol
    -0.71
    ework
    -0.67
     Anaheim
    -0.63
     Kepler
    -0.62
     Pict
    -0.59
    ãĤ¶
    -0.59
    SON
    -0.58
     Wid
    -0.58
     Stef
    -0.57
    POSITIVE LOGITS
     billion
    1.00
    -$
    0.94
    billion
    0.93
     bribe
    0.92
     million
    0.91
     Billion
    0.89
    ultz
    0.85
     dollars
    0.85
    million
    0.85
    illion
    0.82
    Activations Density 0.082%

    No Known Activations