© 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. 16647
    Prev
    Next
    INDEX
    Explanations

    profanity and curse words

    oai_token-act-pair · gpt-3.5-turbo

    intense expressions of profanity

    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
     Flavoring
    -0.81
     behavi
    -0.74
    BIL
    -0.73
    Trust
    -0.73
    Folder
    -0.70
    NetMessage
    -0.70
    anu
    -0.69
     destro
    -0.68
    ãĤ¢ãĥ«
    -0.67
    ACP
    -0.67
    POSITIVE LOGITS
     kidding
    0.99
     retard
    0.81
    holes
    0.79
     idiot
    0.78
     idiots
    0.78
     asshole
    0.77
     hell
    0.75
    ventions
    0.73
     retarded
    0.73
     yeah
    0.71
    Activations Density 0.044%

    No Known Activations