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. 2760
    Prev
    Next
    INDEX
    Explanations

    numbers related to currency amounts

    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
    393
    +0.18
    0.8%
    71
    +0.15
    0.7%
    593
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.18
    0.07
    344
    +0.15
    0.08
    357
    +0.10
    0.06
    Negative Logits
    ĸļ
    -0.90
    acus
    -0.74
    most
    -0.73
    ħĭ
    -0.70
    ļéĨĴ
    -0.69
    dict
    -0.68
    ration
    -0.68
    era
    -0.68
    usp
    -0.67
    GN
    -0.66
    POSITIVE LOGITS
     dollars
    0.97
     times
    0.87
     unanswered
    0.87
     miles
    0.82
     thousands
    0.81
     occasions
    0.80
     opportunities
    0.80
     people
    0.79
     kilometers
    0.78
     kilometres
    0.76
    Activations Density 0.542%

    No Known Activations