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 768
    5. 8-RES_FS768-JB
    6. 10
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters and sports injuries

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    314
    +0.18
    0.8%
    232
    +0.12
    0.5%
    92
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.18
    0.11
    354
    +0.12
    0.10
    145
    +0.10
    0.09
    Negative Logits
     slowing
    -0.70
     disputed
    -0.69
     vain
    -0.68
     suppressed
    -0.67
    etheless
    -0.67
     mixed
    -0.66
     concerted
    -0.66
     conver
    -0.66
     restricted
    -0.65
     cred
    -0.65
    POSITIVE LOGITS
    oran
    0.97
    odor
    0.86
    grid
    0.84
    ophe
    0.82
    sei
    0.81
    iba
    0.80
    opolis
    0.80
    atre
    0.79
    mis
    0.79
    alf
    0.78
    Activations Density 3.090%

    No Known Activations