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. 263
    Prev
    Next
    INDEX
    Explanations

    phrases related to competition and performance evaluation

    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
    331
    +0.12
    0.5%
    218
    +0.11
    0.5%
    671
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    351
    +0.12
    0.11
    331
    +0.11
    0.14
    221
    +0.10
    0.10
    Negative Logits
    itton
    -0.74
    ortment
    -0.67
     assorted
    -0.65
    rather
    -0.65
    almost
    -0.64
    not
    -0.60
     gradually
    -0.60
     rather
    -0.59
     periodically
    -0.59
    probably
    -0.59
    POSITIVE LOGITS
     anymore
    2.22
     nor
    2.04
     whatsoever
    1.55
     slightest
    1.42
     anything
    1.41
     anybody
    1.31
     any
    1.31
     anywhere
    1.27
     necessarily
    1.19
     anyone
    1.14
    Activations Density 6.869%

    No Known Activations