© 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. 26779
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "future."

    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
    459
    +0.13
    0.6%
    571
    +0.11
    0.5%
    141
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    388
    +0.13
    0.02
    141
    +0.11
    0.02
    666
    +0.10
    0.02
    Negative Logits
    azines
    -0.82
    edin
    -0.75
    ideshow
    -0.74
    Fat
    -0.74
    uala
    -0.73
    iasis
    -0.71
    ibu
    -0.70
    tha
    -0.70
    DOS
    -0.70
    cius
    -0.69
    POSITIVE LOGITS
     generations
    1.03
     occupant
    1.02
     outlook
    0.95
     horizon
    0.93
     prospects
    0.90
     occupants
    0.86
     relevance
    0.84
     viability
    0.83
     tense
    0.83
     direction
    0.83
    Activations Density 0.023%

    No Known Activations