© 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. 11-RES-JB
    11. 11874
    Prev
    Next
    INDEX
    Explanations

    instances of a specific character encoding tag

    oai_token-act-pair · gpt-3.5-turbo

    end-of-text tokens

    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
     eleph
    -0.79
     oun
    -0.72
     metic
    -0.70
     citiz
    -0.68
     neighb
    -0.67
     exha
    -0.64
     spitting
    -0.63
     spir
    -0.62
     frontline
    -0.62
     exting
    -0.61
    POSITIVE LOGITS
    Reviewed
    1.17
    Reviewer
    1.16
    Advertisements
    1.11
    Rated
    1.10
    Contents
    1.09
    Welcome
    1.08
    Offline
    1.07
    Located
    1.07
    Introduction
    1.07
    Trivia
    1.06
    Activations Density 0.677%

    No Known Activations