© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-RES-JB
    11. 2687
    Prev
    Next
    INDEX
    Explanations

    offensive language and insults

    oai_token-act-pair · gpt-3.5-turbo

    derogatory terms used to insult individuals or groups

    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
     sequencing
    -0.77
     VIDEOS
    -0.76
     transitions
    -0.76
     exposures
    -0.73
     uninterrupted
    -0.71
     visibility
    -0.71
    rences
    -0.70
    anticipated
    -0.70
    ispers
    -0.68
     arcs
    -0.68
    POSITIVE LOGITS
     hypocr
    1.39
     liar
    1.34
     whore
    1.22
     traitor
    1.21
     bigot
    1.15
     idiot
    1.15
     unworthy
    1.12
    fascist
    1.09
     coward
    1.08
     idiots
    1.04
    Activations Density 0.473%

    No Known Activations