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. 11-RES-JB
    6. 2963
    Prev
    Next
    INDEX
    Explanations

    financial and business terms related to transactions and contracts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of significant financial transactions or payments related to governmental or organizational actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    danger
    -0.78
    osterone
    -0.75
     Comed
    -0.73
    esity
    -0.71
    spir
    -0.70
     purge
    -0.65
     Anxiety
    -0.63
    ghazi
    -0.63
     slept
    -0.62
     ate
    -0.62
    POSITIVE LOGITS
     subcontract
    1.47
     financing
    1.34
     bidding
    1.29
     bids
    1.27
     bidder
    1.27
     consortium
    1.25
     procurement
    1.23
     leases
    1.22
     lease
    1.22
     leasing
    1.18
    Activations Density 0.521%

    No Known Activations