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. 3-RES-JB
    6. 7411
    Prev
    Next
    INDEX
    Explanations

    terms related to bidding in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the bidding process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sheen
    -0.73
    helle
    -0.72
     Metatron
    -0.65
    Jewish
    -0.65
     Meadow
    -0.65
    overy
    -0.64
    士
    -0.63
     Teaching
    -0.63
     Danger
    -0.61
     Beard
    -0.60
    POSITIVE LOGITS
     bidder
    1.15
     bidding
    1.09
     bids
    1.09
    irection
    0.95
     auctions
    0.94
     volunte
    0.82
     Bid
    0.81
    elist
    0.81
     auction
    0.80
    eer
    0.79
    Activations Density 0.010%

    No Known Activations