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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 37112
    Prev
    Next
    INDEX
    Explanations

    mentions of shares in the context of financial discussions

    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
    679
    +0.14
    0.6%
    114
    +0.12
    0.5%
    578
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    578
    +0.14
    0.01
    679
    +0.12
    0.01
    114
    +0.10
    0.01
    Negative Logits
    ALLY
    -0.73
    ²¾
    -0.69
    gery
    -0.67
    istically
    -0.66
    Args
    -0.65
    Ī
    -0.63
    \\\\\\\\\\\\\\\\
    -0.61
     Nost
    -0.60
    Ł
    -0.58
    incarn
    -0.58
    POSITIVE LOGITS
    hips
    1.05
    hare
    0.90
    emonium
    0.83
    hip
    0.81
    holder
    0.80
    holders
    0.79
    cliffe
    0.78
    poons
    0.78
    hops
    0.77
    edin
    0.76
    Activations Density 0.006%

    No Known Activations