© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8-RES-JB
    11. 12982
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating approval or disapproval

    oai_token-act-pair · gpt-3.5-turbo

    terms related to correctness and incorrectness, particularly with the modifiers "rightly," "rightfully," "wrongly," and "falsely."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    iments
    -0.87
    isms
    -0.82
    ĸļ
    -0.80
    arella
    -0.71
    orem
    -0.70
    ista
    -0.69
    actic
    -0.68
    Cra
    -0.68
    iment
    -0.68
     Flavoring
    -0.66
    POSITIVE LOGITS
     priced
    0.94
     construed
    0.85
     charged
    0.84
     represented
    0.82
     punished
    0.82
     entrusted
    0.81
    ãĤ©
    0.80
     apprehended
    0.80
     assessed
    0.79
     rewarded
    0.79
    Activations Density 0.053%

    No Known Activations