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. 23174
    Prev
    Next
    INDEX
    Explanations

    expressions related to missed opportunities or losses

    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
    651
    +0.10
    0.5%
    570
    +0.10
    0.5%
    491
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    504
    +0.10
    0.02
    491
    +0.10
    0.02
    562
    +0.10
    0.02
    Negative Logits
    loo
    -0.72
     Jinping
    -0.65
    optional
    -0.60
    gars
    -0.58
     inferred
    -0.58
    jury
    -0.57
    dh
    -0.57
    rim
    -0.57
    vec
    -0.57
     derog
    -0.55
    POSITIVE LOGITS
    pelled
    1.33
    hap
    1.21
    pelling
    1.12
    pell
    1.11
    peak
    1.02
    poke
    1.02
     deadlines
    0.95
    ouri
    0.94
    auga
    0.80
     opportunities
    0.78
    Activations Density 0.025%

    No Known Activations