© 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. 6322
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contrast or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    contrasting conjunctions that indicate a shift in perspective or introduce a counterpoint

    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
     Difficulty
    -0.75
     Liberties
    -0.69
    oire
    -0.69
    enger
    -0.67
    ungle
    -0.66
     Medals
    -0.62
    vantage
    -0.62
    anamo
    -0.59
     Rover
    -0.59
    ascar
    -0.58
    POSITIVE LOGITS
     nevertheless
    1.41
    chery
    1.37
     nonetheless
    1.37
     undeniably
    1.09
     still
    1.08
    chers
    1.03
     manageable
    1.00
     unmist
    0.99
    tons
    0.93
     effective
    0.91
    Activations Density 0.069%

    No Known Activations