© 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. 9-RES-JB
    11. 13219
    Prev
    Next
    INDEX
    Explanations

    currency units or amounts in various currencies

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and currency amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istical
    -0.67
     Tinker
    -0.65
    ifact
    -0.64
    sburgh
    -0.63
     Able
    -0.61
    Ready
    -0.61
     Buckley
    -0.60
     Dug
    -0.59
    ellar
    -0.59
    opic
    -0.59
    POSITIVE LOGITS
     (£
    1.56
     ($
    1.42
     (~
    1.10
     apiece
    1.03
    pees
    0.99
     sterling
    0.97
    USD
    0.97
    /$
    0.93
    ($
    0.92
     payable
    0.91
    Activations Density 0.074%

    No Known Activations