© 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. 37185
    Prev
    Next
    INDEX
    Explanations

    references to excessive quantities or amounts

    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
    408
    +0.15
    0.7%
    728
    +0.09
    0.4%
    35
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.15
    0.02
    344
    +0.09
    0.02
    252
    +0.09
    0.02
    Negative Logits
    byn
    -0.91
    saf
    -0.89
    selves
    -0.89
    ologies
    -0.88
    Ń·
    -0.86
    ands
    -0.81
    estones
    -0.79
    ospels
    -0.79
    ĪĴ
    -0.77
    İĭ
    -0.76
    POSITIVE LOGITS
     emphasis
    1.05
     attention
    0.96
     firepower
    0.93
     baggage
    0.88
     negativity
    0.88
     inconsistency
    0.86
     concentration
    0.84
     temptation
    0.84
     exposure
    0.83
     fuss
    0.83
    Activations Density 0.023%

    No Known Activations