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. 1108
    Prev
    Next
    INDEX
    Explanations

    information related to upcoming releases or announcements

    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
    579
    +0.12
    0.5%
    272
    +0.10
    0.5%
    592
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.12
    0.07
    76
    +0.10
    0.07
    576
    +0.09
    0.04
    Negative Logits
    ndra
    -0.94
    zsche
    -0.82
    rious
    -0.76
    bol
    -0.72
    antry
    -0.71
    acan
    -0.70
    Leary
    -0.69
    anton
    -0.68
    orsi
    -0.67
    Sym
    -0.65
    POSITIVE LOGITS
     theaters
    1.32
     paperback
    1.29
     ebook
    1.14
     DVD
    1.13
    DVD
    1.10
     iTunes
    1.07
     Kindle
    1.06
     Hulu
    1.03
     formats
    1.03
     subscription
    1.03
    Activations Density 2.117%

    No Known Activations