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 24576
    5. 8-RES_FS24576-JB
    6. 23351
    Prev
    Next
    INDEX
    Explanations

    expressions of personal experiences and feelings

    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
    483
    +0.12
    0.5%
    264
    +0.10
    0.5%
    740
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.12
    0.04
    41
    +0.10
    0.04
    259
    +0.10
    0.03
    Negative Logits
    raltar
    -0.73
    neutral
    -0.71
    planes
    -0.64
    winner
    -0.63
    ãĥ¯ãĥ³
    -0.60
    bis
    -0.57
     scraps
    -0.57
    hea
    -0.55
    iday
    -0.55
    erman
    -0.55
    POSITIVE LOGITS
    inventoryQuantity
    0.70
     compared
    0.67
    ],[
    0.61
     spiritually
    0.61
    Critical
    0.61
    Tip
    0.59
    mouth
    0.59
    Reviewer
    0.58
     mentally
    0.58
    Merit
    0.57
    Activations Density 0.151%

    No Known Activations