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. 19053
    Prev
    Next
    INDEX
    Explanations

    phrases related to policies, guidance, or official positions

    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
    481
    +0.14
    0.6%
    362
    +0.13
    0.6%
    549
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.14
    0.03
    362
    +0.13
    0.03
    647
    +0.09
    0.02
    Negative Logits
    mouth
    -0.74
    du
    -0.72
    flush
    -0.69
    iband
    -0.67
    zon
    -0.67
    quer
    -0.66
    nice
    -0.66
    eware
    -0.65
    zip
    -0.65
    named
    -0.65
    POSITIVE LOGITS
     expectations
    0.92
     tradition
    0.89
     regard
    0.84
    ¥µ
    0.82
     ideals
    0.81
     traditions
    0.79
     regards
    0.79
     what
    0.76
     prevailing
    0.75
     ours
    0.75
    Activations Density 0.075%

    No Known Activations