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. 401
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters and official statements

    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
    490
    +0.11
    0.5%
    313
    +0.11
    0.5%
    85
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    313
    +0.11
    0.09
    131
    +0.11
    0.07
    572
    +0.11
    0.08
    Negative Logits
     needles
    -0.68
    haven
    -0.67
    atus
    -0.65
    edia
    -0.64
     needs
    -0.61
     broom
    -0.60
     sooner
    -0.59
    agogue
    -0.59
    Maker
    -0.58
    Mods
    -0.57
    POSITIVE LOGITS
     remarks
    0.90
     statement
    0.85
     briefing
    0.84
     introductory
    0.79
     quoted
    0.77
     keynote
    0.76
     emailed
    0.76
     comments
    0.73
     newsp
    0.72
    EStream
    0.72
    Activations Density 0.994%

    No Known Activations