Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 1381
    Prev
    Next
    INDEX
    Explanations

    various instances of the word "cock" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "cock" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GOODMAN
    -0.93
    è£ħ
    -0.76
     Grateful
    -0.73
    DragonMagazine
    -0.69
     Parenthood
    -0.67
    PsyNetMessage
    -0.66
    EMBER
    -0.66
     Blessed
    -0.65
     fateful
    -0.62
     kcal
    -0.61
    POSITIVE LOGITS
    roach
    1.29
    pit
    1.10
    tail
    1.08
    crow
    1.07
    cock
    1.05
    mong
    1.04
    tails
    1.01
    haw
    0.90
    atures
    0.89
    oons
    0.88
    Activations Density 0.009%

    No Known Activations