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. 4-RES-JB
    6. 5944
    Prev
    Next
    INDEX
    Explanations

    commands or instructions to perform specific actions, often with the phrase "Be sure to."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that advise caution and encourage checking or following instructions

    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
    ELD
    -0.79
    grounds
    -0.72
    Cre
    -0.65
    impl
    -0.65
    ynthesis
    -0.63
     "$:/
    -0.62
     tainted
    -0.62
    Ell
    -0.61
    alist
    -0.61
     pandemonium
    -0.61
    POSITIVE LOGITS
     caution
    0.78
     preferably
    0.73
     Regarding
    0.71
     Supplement
    0.71
     Prepare
    0.70
     advise
    0.70
     carefully
    0.69
    racuse
    0.68
     caveat
    0.68
     hesitate
    0.68
    Activations Density 0.208%

    No Known Activations