© 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. 11-RES-JB
    11. 9279
    Prev
    Next
    INDEX
    Explanations

    monetary amounts and prices

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and monetary amounts related to fines or costs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isms
    -0.71
     longest
    -0.67
     taller
    -0.64
     caveat
    -0.63
    heading
    -0.63
     geographically
    -0.63
    ilateral
    -0.62
     stride
    -0.61
     prominently
    -0.60
     shortest
    -0.60
    POSITIVE LOGITS
     cents
    1.52
     euros
    1.49
    ¢
    1.37
     dollars
    1.30
    $.
    1.28
     Euros
    1.23
    âĤ¬
    1.23
    $
    1.21
     bucks
    1.20
     Dollars
    1.19
    Activations Density 0.126%

    No Known Activations