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. 2114
    Prev
    Next
    INDEX
    Explanations

    organizations and companies in the tech and finance industries

    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
    640
    +0.18
    0.8%
    314
    +0.15
    0.7%
    679
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.18
    0.13
    640
    +0.15
    0.12
    679
    +0.13
    0.11
    Negative Logits
     withd
    -0.93
     induct
    -0.89
     prototyp
    -0.84
     grounding
    -0.79
     recalled
    -0.78
     chained
    -0.77
     remembered
    -0.77
     stocking
    -0.76
     affili
    -0.75
     electr
    -0.75
    POSITIVE LOGITS
    com
    1.58
    exe
    1.56
    org
    1.54
    jpg
    1.39
    edu
    1.36
    dll
    1.34
    net
    1.34
    png
    1.31
    NET
    1.31
    txt
    1.30
    Activations Density 0.945%

    No Known Activations