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. 43287
    Prev
    Next
    INDEX
    Explanations

    variations of the pronoun "it."

    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
    251
    +0.10
    0.4%
    209
    +0.09
    0.4%
    259
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    259
    +0.10
    0.04
    713
    +0.09
    0.02
    252
    +0.09
    0.03
    Negative Logits
    noticed
    -0.66
    ichever
    -0.65
    herent
    -0.64
    mma
    -0.61
     Friendly
    -0.61
    dding
    -0.60
    cknow
    -0.59
    eligible
    -0.58
    ighton
    -0.55
    tted
    -0.55
    POSITIVE LOGITS
     entails
    1.01
     boils
    0.99
     hurts
    0.96
    alian
    0.92
     happens
    0.91
     happened
    0.90
     transpired
    0.89
     feels
    0.88
     takes
    0.84
     mattered
    0.83
    Activations Density 0.048%

    No Known Activations