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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 1977
    Prev
    Next
    INDEX
    Explanations

    words relating to violence or harm, particularly the act of killing

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of killing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.85
    Cola
    -0.78
    Scot
    -0.75
    ĸļ
    -0.71
    itle
    -0.71
    fty
    -0.70
    DragonMagazine
    -0.69
     Depot
    -0.69
    soType
    -0.67
    rypt
    -0.66
    POSITIVE LOGITS
     spree
    1.00
    mails
    0.85
    switch
    0.84
     civilians
    0.83
    joy
    0.83
     innocent
    0.76
     off
    0.73
    mong
    0.73
     innoc
    0.70
     rampage
    0.70
    Activations Density 0.047%

    No Known Activations