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. 7897
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pricing" at various levels of intensity

    oai_token-act-pair · gpt-3.5-turbo

    references to pricing

    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
    ometown
    -0.87
    san
    -0.75
     Schne
    -0.75
    nee
    -0.75
    icus
    -0.74
    vous
    -0.71
    enegger
    -0.71
    ocent
    -0.70
    uther
    -0.69
     Doe
    -0.68
    POSITIVE LOGITS
     pricing
    1.10
     prices
    1.03
     premiums
    0.94
     gou
    0.92
     tiers
    0.90
     discounts
    0.89
     refunds
    0.87
     arrangements
    0.85
     price
    0.84
     peanuts
    0.82
    Activations Density 0.012%

    No Known Activations