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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 2815
    Prev
    Next
    INDEX
    Explanations

    dates and events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    393
    +0.11
    0.5%
    73
    +0.10
    0.5%
    549
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.11
    0.12
    608
    +0.10
    0.10
    587
    +0.10
    0.09
    Negative Logits
    arers
    -0.71
    entimes
    -0.69
    ographies
    -0.67
    urers
    -0.67
    boxing
    -0.67
    ersive
    -0.67
    phasis
    -0.66
    uto
    -0.66
     nevertheless
    -0.65
    lees
    -0.65
    POSITIVE LOGITS
     RTX
    0.70
     theirs
    0.70
     Omni
    0.69
     Hurricane
    0.67
     Adventures
    0.66
     IEEE
    0.65
     Premiere
    0.65
     Flip
    0.64
     Ubuntu
    0.63
     Dungeons
    0.63
    Activations Density 1.523%

    No Known Activations