© 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. 9-RES-JB
    11. 11248
    Prev
    Next
    INDEX
    Explanations

    information related to the birth dates and places of various individuals

    oai_token-act-pair · gpt-3.5-turbo

    statements about people's birth and existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ologies
    -0.75
     amplification
    -0.74
    oppers
    -0.73
    glers
    -0.72
     stabilization
    -0.72
     Extend
    -0.72
    lements
    -0.70
     HAVE
    -0.69
    ogether
    -0.69
     mitigation
    -0.68
    POSITIVE LOGITS
     born
    1.61
     assassinated
    1.07
     married
    1.02
     famed
    1.00
     baptized
    0.98
     appointed
    0.96
     famous
    0.95
     crowned
    0.94
     originally
    0.94
     murdered
    0.94
    Activations Density 0.220%

    No Known Activations