© 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. 9-RES-JB
    11. 9966
    Prev
    Next
    INDEX
    Explanations

    reports of someone's death or pronouncement as dead

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to death and dying

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icons
    -0.75
    amaru
    -0.73
    ãĥķãĤ¡
    -0.72
    idium
    -0.68
    ãĥ¼ãĤ¯
    -0.67
    umar
    -0.65
    imon
    -0.63
    orers
    -0.63
     boycot
    -0.62
    DragonMagazine
    -0.62
    POSITIVE LOGITS
     tragically
    1.03
     peacefully
    0.92
    bed
    0.89
     mysteriously
    0.89
     psychiat
    0.85
     instantly
    0.83
     unexpectedly
    0.80
    icious
    0.77
     prematurely
    0.76
     EMS
    0.73
    Activations Density 0.093%

    No Known Activations