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. 25592
    Prev
    Next
    INDEX
    Explanations

    ingredients related to food items and recipes

    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
    545
    +0.12
    0.6%
    282
    +0.12
    0.6%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.12
    0.03
    545
    +0.12
    0.03
    326
    +0.10
    0.02
    Negative Logits
    pmwiki
    -0.68
    Leader
    -0.65
     accuser
    -0.62
    Reply
    -0.61
     circumstance
    -0.61
    ļé
    -0.61
     publication
    -0.60
    lihood
    -0.60
     EMS
    -0.60
     disputes
    -0.60
    POSITIVE LOGITS
    poons
    1.15
    kins
    1.13
    poon
    1.10
    cale
    1.05
    cape
    1.01
     cooked
    0.99
    eed
    0.99
    mith
    0.99
    kin
    0.97
    hell
    0.96
    Activations Density 0.050%

    No Known Activations