© 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. 11-RES-JB
    11. 6257
    Prev
    Next
    INDEX
    Explanations

    locations or venues associated with tragic events

    oai_token-act-pair · gpt-3.5-turbo

    locations associated with violent incidents

    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
    DragonMagazine
    -0.73
     STATS
    -0.72
    iencies
    -0.64
    figure
    -0.62
    ploma
    -0.62
    erity
    -0.62
    Quantity
    -0.61
    TeX
    -0.60
    ":"/
    -0.60
    stan
    -0.59
    POSITIVE LOGITS
     frequ
    1.02
     parking
    0.88
     complex
    0.84
     injuring
    0.83
    grounds
    0.80
     compound
    0.80
     doors
    0.79
     gunman
    0.79
     vandal
    0.79
     gates
    0.78
    Activations Density 0.183%

    No Known Activations