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. 25597
    Prev
    Next
    INDEX
    Explanations

    terms related to product specifications and retail information

    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
    496
    +0.12
    0.5%
    373
    +0.11
    0.5%
    150
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    212
    +0.12
    0.02
    288
    +0.11
    0.03
    524
    +0.11
    0.02
    Negative Logits
     Trayvon
    -0.70
    pora
    -0.67
    heid
    -0.64
     hur
    -0.62
     relational
    -0.61
     sovere
    -0.60
     choir
    -0.60
    apo
    -0.60
     Gork
    -0.59
     imperson
    -0.59
    POSITIVE LOGITS
     discontinued
    1.11
     Warranty
    1.00
     specifications
    0.99
     Specifications
    0.99
     date
    0.87
    manufact
    0.86
     warranty
    0.85
    Quantity
    0.84
    Order
    0.83
     packaging
    0.82
    Activations Density 0.077%

    No Known Activations