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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 26370
    Prev
    Next
    INDEX
    Explanations

    references to recipes and cooking instructions

    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
    373
    +0.18
    0.8%
    167
    +0.09
    0.4%
    455
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    647
    +0.18
    0.02
    49
    +0.09
    0.03
    375
    +0.09
    0.01
    Negative Logits
     advis
    -0.82
    Newsletter
    -0.74
     elsewhere
    -0.72
     Rosenstein
    -0.68
     Ethics
    -0.68
    Reporting
    -0.68
    posts
    -0.67
     redacted
    -0.67
    ]).
    -0.67
    SPONSORED
    -0.67
    POSITIVE LOGITS
     beautifully
    1.10
     creamy
    1.04
     versatility
    1.01
    eaturing
    0.96
     customizable
    0.96
     stylish
    0.95
     versatile
    0.93
     perfect
    0.92
     gorgeous
    0.91
     sleek
    0.90
    Activations Density 0.316%

    No Known Activations