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 6144
    5. 8-RES_FS6144-JB
    6. 5448
    Prev
    Next
    INDEX
    Explanations

    specific action verbs related to physical movement

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    240
    +0.11
    0.5%
    13
    +0.10
    0.4%
    314
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    708
    +0.11
    0.03
    230
    +0.10
    0.03
    240
    +0.09
    0.03
    Negative Logits
    encies
    -0.89
    nces
    -0.76
    iling
    -0.71
    iled
    -0.69
    afort
    -0.68
     circumstance
    -0.65
    illian
    -0.64
    anyahu
    -0.64
    cffff
    -0.64
     alloy
    -0.63
    POSITIVE LOGITS
    through
    1.06
    about
    0.98
    ways
    0.91
    own
    0.91
     upright
    0.87
    bow
    0.86
    abouts
    0.83
    bows
    0.82
    itzer
    0.80
    way
    0.79
    Activations Density 0.218%

    No Known Activations