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 3072
    5. 8-RES_FS3072-JB
    6. 2821
    Prev
    Next
    INDEX
    Explanations

    verbs related to communication or interaction

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    184
    +0.12
    0.6%
    665
    +0.11
    0.5%
    372
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.12
    0.18
    184
    +0.11
    0.11
    70
    +0.11
    0.15
    Negative Logits
     suppose
    -0.62
    terday
    -0.56
     namely
    -0.54
     anchored
    -0.54
     hosted
    -0.52
     applied
    -0.52
     viz
    -0.52
     awaited
    -0.51
    she
    -0.51
     requiring
    -0.50
    POSITIVE LOGITS
     oneself
    1.05
     ourselves
    1.03
     yourselves
    1.03
     yourself
    1.00
     them
    0.93
    ulate
    0.89
     themselves
    0.88
    ãĥĥãĥī
    0.82
    igate
    0.81
    iate
    0.80
    Activations Density 2.402%

    No Known Activations