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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 10940
    Prev
    Next
    INDEX
    Explanations

    mentions or references of the term "break" or related words

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "freak."

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

    No Comments

    Negative Logits
     proport
    -0.69
    agi
    -0.66
    ript
    -0.66
    orate
    -0.66
     seiz
    -0.64
     Nikola
    -0.64
     Sapp
    -0.62
     Tsukuyomi
    -0.62
    chwitz
    -0.62
     uncont
    -0.61
    POSITIVE LOGITS
    ishly
    0.88
    entimes
    0.82
    driver
    0.81
    show
    0.79
    Crash
    0.78
    nesses
    0.74
    Hour
    0.73
    beard
    0.72
     Eater
    0.72
    pants
    0.72
    Activations Density 0.053%

    No Known Activations