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 49152
    5. 8-RES_FS49152-JB
    6. 40100
    Prev
    Next
    INDEX
    Explanations

    historical figures and events involving conflict or power struggles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    +0.53
    2.8%
    420
    +0.14
    0.7%
    266
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.53
    0.02
    266
    +0.14
    0.08
    420
    +0.13
    0.05
    Negative Logits
     backend
    -0.77
     Snapchat
    -0.76
     Lyft
    -0.74
    Uber
    -0.71
    ï¸ı
    -0.71
    ebin
    -0.69
     TBD
    -0.69
     blockers
    -0.69
    Kick
    -0.68
     Yelp
    -0.68
    POSITIVE LOGITS
     1912
    1.05
     1932
    1.02
     1938
    1.01
     historian
    1.00
     1939
    1.00
     Protestant
    0.99
     postwar
    0.99
     1922
    0.99
     1936
    0.98
     1914
    0.98
    Activations Density 0.891%

    No Known Activations