© 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. 6-RES-JB
    11. 17765
    Prev
    Next
    INDEX
    Explanations

    words related to insults or derogatory remarks

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to insults or derogatory language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ail
    -0.75
    negie
    -0.73
    ucket
    -0.69
    angler
    -0.67
    ills
    -0.67
    iggle
    -0.66
    rief
    -0.66
    arten
    -0.65
    issue
    -0.65
    ECK
    -0.64
    POSITIVE LOGITS
     insult
    0.97
    ingly
    0.95
     insulted
    0.93
     disrespect
    0.91
     insulting
    0.86
     insults
    0.83
     ridicule
    0.77
    ãĤ¹ãĥĪ
    0.74
    xual
    0.74
     Gaw
    0.73
    Activations Density 0.041%

    No Known Activations