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. 7
    Prev
    Next
    INDEX
    Explanations

    financial terms related to investments and trade

    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
    481
    +0.24
    1.1%
    568
    +0.10
    0.5%
    459
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.24
    0.12
    393
    +0.10
    0.22
    45
    +0.10
    0.08
    Negative Logits
    ocr
    -0.78
    agar
    -0.75
    iatus
    -0.74
    igger
    -0.73
    bole
    -0.68
    onica
    -0.68
    itas
    -0.68
    QB
    -0.66
    rio
    -0.66
    oiler
    -0.64
    POSITIVE LOGITS
     assorted
    0.88
     sidel
    0.75
     secondly
    0.74
     ensuring
    0.71
     alternatively
    0.70
     importantly
    0.69
     countless
    0.68
     Lastly
    0.68
     optionally
    0.68
     additionally
    0.67
    Activations Density 6.681%

    No Known Activations