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. 8-RES-JB
    6. 9567
    Prev
    Next
    INDEX
    Explanations

    the letters "tre" followed by a consonant and then a vowel

    oai_token-act-pair · gpt-3.5-turbo

    words related to movement or travel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     envy
    -0.77
     Tsukuyomi
    -0.72
     skim
    -0.65
     aloud
    -0.62
     hypocr
    -0.62
     Upton
    -0.62
     hypoc
    -0.61
     faint
    -0.60
    ĨĴ
    -0.59
     trillions
    -0.58
    POSITIVE LOGITS
    ï¸ı
    0.99
    ois
    0.82
    andowski
    0.77
    andise
    0.77
    essional
    0.75
    anium
    0.73
    icons
    0.73
    idation
    0.73
    onding
    0.71
    undo
    0.71
    Activations Density 0.124%

    No Known Activations