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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 19064
    Prev
    Next
    INDEX
    Explanations

    specific locations and government-related terms

    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
    +0.55
    3.0%
    266
    +0.12
    0.7%
    51
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.55
    0.02
    362
    +0.12
    0.08
    266
    +0.10
    0.07
    Negative Logits
     nods
    -0.73
     coincidence
    -0.70
    Legend
    -0.64
    verb
    -0.64
     resemb
    -0.63
    èĢħ
    -0.60
    æĺ¯
    -0.57
     congratulations
    -0.57
     compliments
    -0.57
     inspiration
    -0.57
    POSITIVE LOGITS
     workforce
    0.92
     industries
    0.83
     households
    0.79
     sector
    0.78
     infrastructure
    0.77
     constituencies
    0.77
     healthcare
    0.76
     sectors
    0.76
     provinces
    0.75
     population
    0.73
    Activations Density 0.635%

    No Known Activations