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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 16504
    Prev
    Next
    INDEX
    Explanations

    references to the word "Killer"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "killer" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ational
    -0.93
    ional
    -0.89
    bles
    -0.82
    herty
    -0.81
    heny
    -0.77
    uration
    -0.76
    ourced
    -0.75
    ibly
    -0.74
    erous
    -0.72
    ury
    -0.71
    POSITIVE LOGITS
     instinct
    0.94
    killer
    0.90
     spree
    0.84
    knife
    0.83
     whales
    0.81
     intent
    0.78
     whale
    0.78
    mails
    0.76
     blow
    0.74
     Killer
    0.74
    Activations Density 0.059%

    No Known Activations