© 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 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. 11-RES-JB
    11. 7493
    Prev
    Next
    INDEX
    Explanations

    words related to negative judgments and criticism

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that express strong criticism or condemnation

    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
    foreseen
    -0.72
    accompan
    -0.70
     eased
    -0.61
     experien
    -0.59
    earchers
    -0.58
    affected
    -0.56
     quieter
    -0.56
     Doors
    -0.56
    Enlarge
    -0.56
     restless
    -0.56
    POSITIVE LOGITS
     hypocrisy
    1.08
     hypocritical
    0.93
     hypoc
    0.93
     hypocr
    0.91
     stupidity
    0.91
     coward
    0.91
    !!"
    0.90
     arrogance
    0.88
     slander
    0.85
    !!!!
    0.83
    Activations Density 0.270%

    No Known Activations