© 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. 0-RES-JB
    11. 1128
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or investigative processes such as inquests, autopsies, and coroners

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal investigations and medical examinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zone
    -0.66
     buffer
    -0.65
    utive
    -0.65
    hammad
    -0.64
    itely
    -0.64
    ubes
    -0.62
     Shop
    -0.62
    ateful
    -0.62
     Sponge
    -0.61
    actus
    -0.61
    POSITIVE LOGITS
     coron
    3.78
     inquest
    2.52
     coroner
    2.17
     autopsy
    2.08
    mortem
    1.28
     christ
    1.20
     funer
    1.09
     herald
    1.08
     cull
    1.05
     funeral
    0.97
    Activations Density 0.058%

    No Known Activations