© 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. 24011
    Prev
    Next
    INDEX
    Explanations

    instances of the word "same" and its variations

    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
    373
    +0.10
    0.5%
    408
    +0.09
    0.4%
    253
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    162
    +0.10
    0.03
    95
    +0.09
    0.03
    423
    +0.09
    0.03
    Negative Logits
    *=-
    -0.65
    skirts
    -0.64
    live
    -0.64
     Provided
    -0.63
    Interstitial
    -0.61
    âĵĺ
    -0.61
    ifest
    -0.60
     Recomm
    -0.59
    aze
    -0.59
    phasis
    -0.58
    POSITIVE LOGITS
     vein
    0.98
     thing
    0.93
     exact
    0.93
     kind
    0.82
     timeframe
    0.73
     sort
    0.72
     old
    0.70
     amount
    0.69
     type
    0.68
     scenario
    0.68
    Activations Density 0.031%

    No Known Activations