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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 1194
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences beginning with "There is."

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    20
    +0.13
    0.6%
    126
    +0.11
    0.5%
    398
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    20
    +0.13
    0.12
    126
    +0.11
    0.10
    398
    +0.10
    0.09
    Negative Logits
    ares
    -0.67
    strip
    -0.58
    bies
    -0.57
    BI
    -0.57
    icut
    -0.56
    buster
    -0.55
    eal
    -0.55
     towed
    -0.55
     bombed
    -0.55
    tumblr
    -0.55
    POSITIVE LOGITS
     plenty
    1.08
     ample
    0.97
     no
    0.89
     overlap
    0.86
     precedent
    0.83
    女
    0.81
     lots
    0.81
     disagreement
    0.79
     variability
    0.78
     similarities
    0.78
    Activations Density 1.278%

    No Known Activations