Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 23901
    Prev
    Next
    INDEX
    Explanations

    words that contain the suffix "ick."

    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
    276
    +0.13
    0.6%
    374
    +0.10
    0.5%
    438
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    230
    +0.13
    0.01
    326
    +0.10
    0.01
    374
    +0.10
    0.00
    Negative Logits
    BuyableInstoreAndOnline
    -0.88
    ATIONAL
    -0.71
    orescence
    -0.64
     Lif
    -0.64
     warr
    -0.63
     Fisheries
    -0.63
     Mazda
    -0.62
    ATIONS
    -0.62
     LIFE
    -0.62
     Lauder
    -0.61
    POSITIVE LOGITS
    ilver
    1.38
    haw
    1.29
    icks
    1.03
    eter
    0.99
    hire
    0.98
    ety
    0.95
    icking
    0.94
    olls
    0.91
    eters
    0.90
    etts
    0.90
    Activations Density 0.007%

    No Known Activations