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. 2364
    Prev
    Next
    INDEX
    Explanations

    baseball-related terms and activities

    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
    575
    +0.13
    0.6%
    718
    +0.11
    0.5%
    26
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.07
    288
    +0.11
    0.08
    26
    +0.10
    0.06
    Negative Logits
    mble
    -0.79
     Beir
    -0.77
    riott
    -0.77
    romeda
    -0.76
    ë
    -0.75
     Imperium
    -0.74
    iveness
    -0.72
    ively
    -0.70
    iencies
    -0.70
    liness
    -0.70
    POSITIVE LOGITS
     pitcher
    1.19
     pitchers
    1.16
    BIP
    1.03
     batters
    1.01
     pitching
    1.00
     batted
    0.98
     hitters
    0.97
     hitter
    0.97
     reliever
    0.96
     batter
    0.90
    Activations Density 0.902%

    No Known Activations