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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3927
    Prev
    Next
    INDEX
    Explanations

    numeric values combined with units of measurement

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    quantified amounts or values related to money and numerical figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     omission
    -0.71
    ItemImage
    -0.70
     conveyed
    -0.67
     longest
    -0.66
     prominently
    -0.62
     transmitted
    -0.61
    channelAvailability
    -0.59
     mismatch
    -0.59
     length
    -0.58
    QUIRE
    -0.57
    POSITIVE LOGITS
     cents
    1.41
     bucks
    1.32
    ¢
    1.24
     dollars
    1.16
    $.
    1.15
    $,
    1.14
     euros
    1.13
     Dollars
    1.10
     Euros
    1.07
    $
    1.04
    Activations Density 0.123%

    No Known Activations