© 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. 1-RES-JB
    11. 5307
    Prev
    Next
    INDEX
    Explanations

    explicitly profane language

    oai_token-act-pair · gpt-3.5-turbo

    explicit language expressing strong emotions or frustrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewed
    -0.74
    perse
    -0.72
    NetMessage
    -0.72
     circ
    -0.71
    士
    -0.70
    rive
    -0.67
     conve
    -0.64
    Newsletter
    -0.62
    iche
    -0.62
    unc
    -0.61
    POSITIVE LOGITS
    fuck
    1.36
     fuck
    1.18
    holes
    1.01
    hole
    0.99
     Fuck
    0.94
    Fuck
    0.92
     FUCK
    0.91
    dump
    0.85
     kidding
    0.82
    mers
    0.82
    Activations Density 0.011%

    No Known Activations