© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 16822
    Prev
    Next
    INDEX
    Explanations

    keywords related to different types of cards, such as Railcard, Mastercard, and Wildcard

    oai_token-act-pair · gpt-3.5-turbo

    references to credit cards

    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
     webs
    -0.72
     righteousness
    -0.62
     Babel
    -0.62
     Wash
    -0.60
    isy
    -0.60
     nests
    -0.59
     oppos
    -0.58
     dirt
    -0.58
     opposition
    -0.58
     spac
    -0.56
    POSITIVE LOGITS
    card
    4.59
    cards
    3.37
    Card
    2.69
     card
    2.25
     CARD
    2.12
     Card
    2.07
     cards
    1.77
    deck
    1.68
     Cards
    1.61
    ocard
    1.28
    Activations Density 0.009%

    No Known Activations