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 3072
    5. 8-RES_FS3072-JB
    6. 1498
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions or agreements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    608
    +0.19
    0.9%
    362
    +0.14
    0.6%
    620
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.19
    0.13
    362
    +0.14
    0.10
    88
    +0.11
    0.07
    Negative Logits
    edin
    -0.82
    cles
    -0.79
    beat
    -0.72
    zona
    -0.72
    aan
    -0.71
    chenko
    -0.69
    ault
    -0.69
    ONSORED
    -0.69
    nick
    -0.69
    qi
    -0.68
    POSITIVE LOGITS
    bidden
    1.24
     starters
    1.06
    geries
    1.05
    gotten
    0.99
     those
    0.99
    gery
    0.95
     purposes
    0.93
     beginners
    0.92
     us
    0.91
     anyone
    0.90
    Activations Density 0.730%

    No Known Activations