© 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. 2-RES-JB
    11. 17470
    Prev
    Next
    INDEX
    Explanations

    profane language

    oai_token-act-pair · gpt-3.5-turbo

    expressions of frustration or disdain towards things perceived as nonsensical or worthless

    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
    hip
    -0.92
    sole
    -0.75
    vim
    -0.75
    significant
    -0.73
    versible
    -0.73
    lez
    -0.69
    ugal
    -0.69
    expression
    -0.69
    rez
    -0.69
    tein
    -0.69
    POSITIVE LOGITS
     crap
    1.05
     bullshit
    0.98
     BS
    0.98
     blah
    0.94
     nonsense
    0.93
     rubbish
    0.92
     excuse
    0.89
     excuses
    0.81
     Jindal
    0.77
    ocr
    0.70
    Activations Density 0.006%

    No Known Activations