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. 1223
    Prev
    Next
    INDEX
    Explanations

    references to the legalization and culture surrounding marijuana, including related terms like 'THC', 'pot', 'cultivation', and 'recreational use'

    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
    481
    +0.18
    0.8%
    288
    +0.13
    0.6%
    447
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    461
    +0.18
    0.07
    288
    +0.13
    0.08
    67
    +0.12
    0.07
    Negative Logits
     Stevenson
    -0.80
     Rove
    -0.71
     Stevens
    -0.70
     Krug
    -0.68
     Coul
    -0.67
     partName
    -0.67
     Laurent
    -0.67
    Ble
    -0.65
     Wiley
    -0.65
    umm
    -0.64
    POSITIVE LOGITS
     legalization
    1.27
     dispensaries
    1.15
     cultivation
    1.04
     dispensary
    0.99
    arijuana
    0.99
     prohibition
    0.97
     marijuana
    0.90
     decriminal
    0.86
     smokers
    0.84
     cigarettes
    0.83
    Activations Density 0.612%

    No Known Activations