© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 8384
    Prev
    Next
    INDEX
    Explanations

    profanity and oaths

    oai_token-act-pair · gpt-3.5-turbo

    instances of swearing or cursing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Northwestern
    -0.67
     Pioneer
    -0.67
    Fab
    -0.67
     Seed
    -0.66
     seed
    -0.64
     prototype
    -0.64
     Cater
    -0.63
     Safari
    -0.63
    erella
    -0.63
     Marin
    -0.61
    POSITIVE LOGITS
     swearing
    4.00
     cursing
    2.35
     yelling
    1.43
     swore
    1.36
     swear
    1.36
     shouting
    1.27
     perjury
    1.19
    uty
    1.16
     barking
    1.14
     spitting
    1.14
    Activations Density 0.038%

    No Known Activations