© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 14135
    Prev
    Next
    INDEX
    Explanations

    profanities

    oai_token-act-pair · gpt-3.5-turbo

    expressions of frustration or disbelief, particularly with the word 'fuck' being used frequently

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -0.75
    Reviewed
    -0.68
    perse
    -0.67
     circ
    -0.63
    rive
    -0.62
    BIL
    -0.62
    Joy
    -0.61
    ACP
    -0.61
     rece
    -0.60
    1963
    -0.58
    POSITIVE LOGITS
    holes
    1.17
    fuck
    1.15
    hole
    1.07
     fuck
    0.99
    bags
    0.88
    dump
    0.88
    cats
    0.86
    buster
    0.85
    owship
    0.81
    bag
    0.81
    Activations Density 0.006%

    No Known Activations