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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 16601
    Prev
    Next
    INDEX
    Explanations

    medical situations or incidents where someone is declared dead or pronounced dead

    oai_token-act-pair · gpt-3.5-turbo

    terms related to death and formal declarations of status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esson
    -0.69
    natureconservancy
    -0.66
     Zup
    -0.66
    umbing
    -0.64
    onse
    -0.62
    si
    -0.62
    isson
    -0.60
    imony
    -0.60
    ":"/
    -0.60
    inement
    -0.59
    POSITIVE LOGITS
     ineligible
    1.09
     unfit
    1.08
     incompetent
    1.07
     dead
    1.06
     invalid
    1.02
     bankrupt
    0.99
     deceased
    0.99
     extinct
    0.98
     obsolete
    0.98
     inactive
    0.95
    Activations Density 0.113%

    No Known Activations