© 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. 37512
    Prev
    Next
    INDEX
    Explanations

    phrases related to events, deadlines, and winners in contests

    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
    +0.12
    0.6%
    756
    +0.10
    0.5%
    317
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    677
    +0.12
    0.03
    726
    +0.10
    0.03
    723
    +0.09
    0.03
    Negative Logits
    inventoryQuantity
    -0.85
    esides
    -0.72
    warts
    -0.72
    isky
    -0.70
    schild
    -0.64
    ebus
    -0.63
    hov
    -0.63
    anship
    -0.62
    hab
    -0.62
    ccording
    -0.62
    POSITIVE LOGITS
     TBD
    0.84
     receipt
    0.78
     TBA
    0.78
     invoice
    0.78
     whichever
    0.78
     discretion
    0.77
     accordingly
    0.77
     thereafter
    0.74
     notification
    0.72
    .<
    0.71
    Activations Density 0.211%

    No Known Activations