Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 18794
    Prev
    Next
    INDEX
    Explanations

    references to draft-related topics, specifically the word "draft"

    oai_token-act-pair · gpt-3.5-turbo

    references to the NFL draft and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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

    Negative Logits
     membr
    -0.78
    combe
    -0.76
    quit
    -0.70
     hem
    -0.68
    emade
    -0.67
    comed
    -0.66
     charism
    -0.64
     sonic
    -0.63
     ful
    -0.63
     Lanc
    -0.63
    POSITIVE LOGITS
     lottery
    1.17
    smanship
    1.10
    Kings
    1.09
     picks
    1.03
     Picks
    0.98
    raft
    0.83
    Express
    0.83
    Draft
    0.83
     Prediction
    0.80
     selections
    0.78
    Activations Density 0.029%

    No Known Activations