© 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 24576
    9. 8-RES_FS24576-JB
    11. 23942
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to calories and consumption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    421
    +0.13
    0.6%
    526
    +0.11
    0.5%
    57
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    421
    +0.13
    0.03
    588
    +0.11
    0.02
    57
    +0.11
    0.01
    Negative Logits
     Alph
    -0.72
     Accountability
    -0.71
     Parish
    -0.67
     Methodist
    -0.65
     Rez
    -0.65
    OVA
    -0.64
    anto
    -0.62
     Interest
    -0.61
     Hills
    -0.61
     Rockefeller
    -0.61
    POSITIVE LOGITS
    culated
    1.04
    ptions
    1.01
    uable
    1.00
    ptive
    0.98
    ming
    0.97
    mer
    0.95
    kered
    0.94
    pering
    0.89
    cul
    0.88
    mers
    0.88
    Activations Density 0.040%

    No Known Activations