© 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. 4-RES-JB
    11. 20249
    Prev
    Next
    INDEX
    Explanations

    profane words

    oai_token-act-pair · gpt-3.5-turbo

    the word "fuck" and its variations, indicating strong emotional expressions or emphasis

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

    No Comments

    Negative Logits
    NetMessage
    -0.73
    rouse
    -0.68
    Reviewed
    -0.66
    perse
    -0.64
    HCR
    -0.64
    BIL
    -0.64
    ItemThumbnailImage
    -0.64
    PsyNetMessage
    -0.63
     Scotia
    -0.62
    NH
    -0.62
    POSITIVE LOGITS
    holes
    1.18
    hole
    1.11
    fuck
    1.00
    bags
    0.90
    opot
    0.90
    nuts
    0.88
    lord
    0.88
    loads
    0.82
    wit
    0.82
    cats
    0.81
    Activations Density 0.008%

    No Known Activations