© 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. 6058
    Prev
    Next
    INDEX
    Explanations

    mentions of family members, specifically children and grandchildren

    oai_token-act-pair · gpt-3.5-turbo

    references to children and family structures

    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
    pmwiki
    -0.84
     corrosion
    -0.63
    ffiti
    -0.62
     vandalism
    -0.61
     constitu
    -0.60
    doors
    -0.59
    Water
    -0.57
    cers
    -0.57
     plagiar
    -0.57
    trak
    -0.57
    POSITIVE LOGITS
     grandchildren
    1.06
     born
    1.01
    iblings
    0.99
     conceived
    0.98
     aged
    0.97
     unborn
    0.95
     whom
    0.93
     together
    0.92
     daughters
    0.92
     eldest
    0.91
    Activations Density 0.104%

    No Known Activations