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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 525
    Prev
    Next
    INDEX
    Explanations

    statements of political events and opinions

    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
    218
    +0.13
    0.6%
    476
    +0.13
    0.6%
    59
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    476
    +0.13
    0.07
    362
    +0.13
    0.09
    59
    +0.10
    0.06
    Negative Logits
    ettle
    -0.90
    onica
    -0.79
    ledged
    -0.74
    ovan
    -0.73
    amed
    -0.70
    ards
    -0.70
    erie
    -0.70
    coins
    -0.68
    ophe
    -0.68
    iva
    -0.67
    POSITIVE LOGITS
     periods
    1.10
     renovations
    1.02
     adolescence
    0.99
     halftime
    0.98
     daylight
    0.95
     infancy
    0.93
     wartime
    0.91
     emergencies
    0.90
     weekends
    0.88
     Ramadan
    0.86
    Activations Density 1.676%

    No Known Activations