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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 6301
    Prev
    Next
    INDEX
    Explanations

    financial amounts presented in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and associated figures in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wart
    -0.80
    aden
    -0.77
    warts
    -0.74
    ocy
    -0.74
    yrinth
    -0.72
    anim
    -0.69
    ciplinary
    -0.68
    omen
    -0.67
    tower
    -0.67
    ression
    -0.66
    POSITIVE LOGITS
     $
    1.79
     ¥
    1.60
     £
    1.56
     âĤ¬
    1.47
     Rs
    1.35
     "$
    1.31
    $
    1.28
     $$
    1.26
    =$
    1.23
     $(
    1.22
    Activations Density 0.116%

    No Known Activations