© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 25771
    Prev
    Next
    INDEX
    Explanations

    references to posthumous occurrences or actions

    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
    +0.13
    0.6%
    7
    +0.12
    0.5%
    288
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    239
    +0.13
    0.01
    368
    +0.12
    0.01
    7
    +0.12
    0.01
    Negative Logits
     lawy
    -0.70
     hypert
    -0.70
    hold
    -0.69
     Hyde
    -0.66
     Trader
    -0.66
    houses
    -0.66
    HOU
    -0.65
    Dim
    -0.63
     Ashton
    -0.61
     Rivals
    -0.61
    POSITIVE LOGITS
    ously
    1.23
    itionally
    1.01
    iliation
    0.93
    ous
    0.91
    osity
    0.90
    onial
    0.89
    inating
    0.87
    inated
    0.86
    ose
    0.85
    pletion
    0.83
    Activations Density 0.003%

    No Known Activations