© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 4249
    Prev
    Next
    INDEX
    Explanations

    if a person has been declared dead or pronounced dead

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms related to medical assessments and rulings regarding life status or health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    inement
    -0.65
     Zup
    -0.63
    yip
    -0.62
    enhagen
    -0.61
     contrasts
    -0.61
    onnaissance
    -0.60
     briefings
    -0.60
     Blackburn
    -0.60
    umbing
    -0.60
    POSITIVE LOGITS
     ineligible
    1.20
     unfit
    1.15
     incompetent
    1.07
     ineffective
    1.05
     invalid
    1.04
     bankrupt
    1.03
     incapable
    1.03
     unus
    1.03
     dead
    1.01
     useless
    1.00
    Activations Density 0.165%

    No Known Activations