© 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. 10608
    Prev
    Next
    INDEX
    Explanations

    profane language and swear words

    oai_token-act-pair · gpt-3.5-turbo

    instances of strong profanity

    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
    inel
    -0.78
    eus
    -0.76
    anu
    -0.73
    Msg
    -0.73
    ère
    -0.73
    Var
    -0.71
    Mesh
    -0.71
    BIL
    -0.71
    idon
    -0.70
    NetMessage
    -0.69
    POSITIVE LOGITS
     fucking
    1.00
     kidding
    0.92
     fuck
    0.84
     goddamn
    0.84
     shit
    0.84
     fuckin
    0.82
     FUCK
    0.81
     prick
    0.81
     piss
    0.78
     asshole
    0.78
    Activations Density 0.016%

    No Known Activations