© 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. 18690
    Prev
    Next
    INDEX
    Explanations

    details about individuals who have died or been pronounced dead

    oai_token-act-pair · gpt-3.5-turbo

    instances of death and related medical terminology

    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
    adian
    -0.66
     boycot
    -0.64
     contrace
    -0.63
    idth
    -0.63
    arity
    -0.62
    orum
    -0.61
    artisan
    -0.60
    tailed
    -0.59
    idates
    -0.58
     bribes
    -0.58
    POSITIVE LOGITS
     instantly
    1.04
     paramedics
    0.86
     shortly
    0.82
     EMS
    0.82
     peacefully
    0.79
     inhal
    0.74
    mediately
    0.73
     immediately
    0.73
     cardiac
    0.73
    aneously
    0.71
    Activations Density 0.086%

    No Known Activations