© 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. 20749
    Prev
    Next
    INDEX
    Explanations

    family relationships, particularly between parents and children

    oai_token-act-pair · gpt-3.5-turbo

    mentions of family relationships, particularly involving mothers, fathers, and children

    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
    ALLY
    -0.89
     Flavoring
    -0.83
    çIJ
    -0.72
    planes
    -0.70
    entin
    -0.70
    ĪĴ
    -0.69
    iannopoulos
    -0.64
    ibly
    -0.63
    ISH
    -0.61
    FORE
    -0.61
    POSITIVE LOGITS
    daughter
    1.28
     daughter
    1.18
     daughters
    1.15
     son
    1.12
     child
    1.05
     grandmother
    1.02
     sons
    1.00
    son
    0.97
     baby
    0.97
     grandparents
    0.96
    Activations Density 0.108%

    No Known Activations