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. 7472
    Prev
    Next
    INDEX
    Explanations

    actions related to offers, negotiations, and discussions in a business context

    oai_token-act-pair · gpt-3.5-turbo

    references to job offers and negotiations

    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
    icka
    -0.87
    ctic
    -0.81
    rity
    -0.76
    ahi
    -0.75
     Oops
    -0.75
    nsic
    -0.72
    ghazi
    -0.71
    idem
    -0.69
    raint
    -0.68
    worn
    -0.68
    POSITIVE LOGITS
     bids
    1.04
     bidding
    1.03
     bid
    0.97
     lucrative
    0.94
     bidder
    0.93
     loan
    0.90
     relocate
    0.87
     hire
    0.84
     offer
    0.80
    soDeliveryDate
    0.80
    Activations Density 0.498%

    No Known Activations