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. 0-RES-JB
    6. 5998
    Prev
    Next
    INDEX
    Explanations

    phrases related to deals and agreements

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Deal," particularly in relation to specific policies or agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ir
    -0.67
     validated
    -0.62
     posterior
    -0.62
     indigenous
    -0.62
     ub
    -0.62
     RS
    -0.62
    orian
    -0.62
    jar
    -0.61
     phosphorus
    -0.61
     oxygen
    -0.61
    POSITIVE LOGITS
     Deal
    4.21
    Deal
    2.87
    deal
    2.71
     Deals
    2.27
     Dealer
    1.97
     deal
    1.93
     deals
    1.58
    deals
    1.57
     Offer
    1.22
     bargain
    1.21
    Activations Density 0.012%

    No Known Activations