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 24576
    5. 8-RES_FS24576-JB
    6. 8386
    Prev
    Next
    INDEX
    Explanations

    mentions of people and their actions or characteristics

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    480
    +0.51
    2.6%
    266
    +0.11
    0.6%
    0
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.51
    0.01
    566
    +0.11
    0.07
    266
    +0.10
    0.08
    Negative Logits
     implying
    -0.60
     clarification
    -0.60
     clarified
    -0.60
     implication
    -0.58
     visc
    -0.57
     refinement
    -0.57
    ĸļ
    -0.56
    Dialogue
    -0.56
    Translation
    -0.55
     formulations
    -0.55
    POSITIVE LOGITS
     subscribing
    0.83
     binge
    0.78
     browsing
    0.77
     commute
    0.76
     shopping
    0.76
     subscribed
    0.75
     commuting
    0.73
     surfing
    0.71
     trek
    0.71
     buying
    0.69
    Activations Density 0.848%

    No Known Activations