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. 26227
    Prev
    Next
    INDEX
    Explanations

    phrases indicating requirement or necessity

    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
    +0.17
    0.8%
    38
    +0.10
    0.5%
    745
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.17
    0.04
    105
    +0.10
    0.03
    551
    +0.10
    0.03
    Negative Logits
     americ
    -0.74
     diction
    -0.68
    cart
    -0.67
    oci
    -0.65
    Liter
    -0.65
    cript
    -0.65
     concess
    -0.64
    laughter
    -0.62
    """
    -0.61
    uras
    -0.61
    POSITIVE LOGITS
     prove
    1.00
     regain
    0.94
     overcome
    0.93
     patience
    0.91
     convince
    0.90
     hurry
    0.86
     rematch
    0.86
     retake
    0.84
     succeed
    0.80
     earn
    0.80
    Activations Density 0.111%

    No Known Activations