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. 41328
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and treatments

    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
    503
    +0.12
    0.5%
    169
    +0.09
    0.4%
    198
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.07
    564
    +0.09
    0.04
    365
    +0.09
    0.02
    Negative Logits
    20439
    -0.77
    lihood
    -0.71
    ortium
    -0.70
    Thumbnail
    -0.67
    hi
    -0.65
    soever
    -0.62
    xon
    -0.62
    lb
    -0.61
    osphere
    -0.61
    thens
    -0.59
    POSITIVE LOGITS
     equivalents
    0.93
     modifiers
    0.86
     versions
    0.80
     terminology
    0.79
     basics
    0.78
     emergencies
    0.77
     exhaustion
    0.75
     fatigue
    0.73
     alternatives
    0.72
     pointers
    0.72
    Activations Density 0.266%

    No Known Activations