© 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. 9-RES-JB
    11. 19796
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "suck" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    the various forms of the verb "suck" and its usage in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ouf
    -0.78
    DonaldTrump
    -0.70
    nda
    -0.69
    tis
    -0.65
    iferation
    -0.64
     Pavilion
    -0.64
    isable
    -0.63
     rall
    -0.63
    DragonMagazine
    -0.60
    ================================================================
    -0.60
    POSITIVE LOGITS
     dick
    0.99
    asses
    0.94
    driver
    0.92
    loads
    0.85
     suck
    0.84
    drivers
    0.81
    sylvania
    0.80
    tails
    0.79
    eries
    0.77
    shit
    0.76
    Activations Density 0.043%

    No Known Activations