© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9482
    Prev
    Next
    INDEX
    Explanations

    information about where individuals were born and where they grew up

    oai_token-act-pair · gpt-3.5-turbo

    biographical information about individuals, including their birth places and family backgrounds

    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
     Reloaded
    -0.89
    mbuds
    -0.78
    uggest
    -0.75
     impunity
    -0.74
    forcement
    -0.74
    ebin
    -0.68
     takedown
    -0.67
     exoner
    -0.67
     CoC
    -0.66
     WARN
    -0.64
    POSITIVE LOGITS
     eldest
    1.14
     educated
    1.05
     upbringing
    1.03
     maternal
    1.01
     born
    0.95
     baptized
    0.94
     parents
    0.92
     youngest
    0.91
     paternal
    0.91
     bapt
    0.87
    Activations Density 0.194%

    No Known Activations