© 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. 10-RES-JB
    11. 3196
    Prev
    Next
    INDEX
    Explanations

    phrases denoting comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "both in" or references to comparisons involving "both."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eday
    -0.70
    @#
    -0.70
     somehow
    -0.70
     instead
    -0.69
     someday
    -0.69
    urs
    -0.68
    something
    -0.68
     nowhere
    -0.68
     accordingly
    -0.67
     likewise
    -0.67
    POSITIVE LOGITS
     sexes
    1.16
     genders
    0.98
     sender
    0.74
     Houses
    0.68
     coasts
    0.66
     physical
    0.65
     chronological
    0.62
    BuyableInstoreAndOnline
    0.61
     sides
    0.61
     Seller
    0.61
    Activations Density 0.182%

    No Known Activations