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. 23911
    Prev
    Next
    INDEX
    Explanations

    specific objects or entities, particularly in contexts related to injury or medical conditions

    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
    481
    +0.19
    0.9%
    288
    +0.14
    0.7%
    87
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.08
    575
    +0.14
    0.06
    519
    +0.13
    0.04
    Negative Logits
    yss
    -0.68
    )?
    -0.59
    addons
    -0.58
     )]
    -0.57
     ?)
    -0.56
    ').
    -0.56
     discretion
    -0.55
     Administ
    -0.54
     disclaim
    -0.54
    )\
    -0.53
    POSITIVE LOGITS
     featuring
    0.67
     replica
    0.67
     WITHOUT
    0.65
     alongside
    0.65
     sandwic
    0.65
    *.
    0.63
     consisting
    0.63
     flanked
    0.63
     while
    0.63
     shortly
    0.62
    Activations Density 0.337%

    No Known Activations