© 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. 9-RES-JB
    11. 11261
    Prev
    Next
    INDEX
    Explanations

    phrases related to opinions or judgments about something being right or just

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that convey notions of correctness or justification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.76
    iments
    -0.72
    amen
    -0.68
    oen
    -0.65
    utenberg
    -0.65
     fertility
    -0.61
    okin
    -0.61
     Vin
    -0.61
     formations
    -0.61
    ynthesis
    -0.61
    POSITIVE LOGITS
     priced
    0.90
     blamed
    0.86
    ãĤ©
    0.85
     labelled
    0.83
     conclude
    0.83
    assert
    0.83
     titled
    0.82
     labeled
    0.81
     judged
    0.79
     guessed
    0.78
    Activations Density 0.088%

    No Known Activations