© 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. 7392
    Prev
    Next
    INDEX
    Explanations

    offensive language

    oai_token-act-pair · gpt-3.5-turbo

    derogatory terms directed at individuals in discussions about social issues

    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
    ļéĨĴ
    -0.87
    »Ĵ
    -0.77
    tions
    -0.73
     streamlined
    -0.67
     exting
    -0.66
     srf
    -0.65
    ActionCode
    -0.63
    Reviewer
    -0.63
    ă
    -0.61
    ü
    -0.61
    POSITIVE LOGITS
     congratulations
    0.73
     sorry
    0.71
     surely
    0.67
     kidding
    0.67
     damned
    0.67
    sorry
    0.66
    Wr
    0.66
     Well
    0.65
     Wrong
    0.64
     liar
    0.62
    Activations Density 0.326%

    No Known Activations