© 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. 0-RES-JB
    11. 8370
    Prev
    Next
    INDEX
    Explanations

    strong, colloquial language or profanity

    oai_token-act-pair · gpt-3.5-turbo

    informal and derogatory language expressing frustration or disdain

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otte
    -0.73
    ello
    -0.70
     Edmund
    -0.66
     Windsor
    -0.66
     Kepler
    -0.64
    ovo
    -0.62
     Townsend
    -0.60
    osen
    -0.60
    omen
    -0.60
     Include
    -0.60
    POSITIVE LOGITS
     shit
    3.82
     crap
    3.27
     Shit
    2.65
    shit
    2.56
     bullshit
    2.21
     fuck
    2.18
     piss
    2.01
     fucking
    2.01
     shitty
    1.93
     stuff
    1.84
    Activations Density 0.013%

    No Known Activations