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. 6-RES-JB
    6. 10628
    Prev
    Next
    INDEX
    Explanations

    verbs related to causing harm or destruction

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of killing or discussions surrounding it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.83
    DragonMagazine
    -0.73
    ĸļ
    -0.69
    Cola
    -0.67
    Scot
    -0.67
    gow
    -0.66
     Failure
    -0.66
    rypt
    -0.66
    oday
    -0.64
    fty
    -0.64
    POSITIVE LOGITS
     spree
    1.04
    joy
    0.85
    switch
    0.82
    mails
    0.79
     off
    0.74
     civilians
    0.73
    blow
    0.72
    req
    0.72
     rampage
    0.71
     zombies
    0.69
    Activations Density 0.048%

    No Known Activations