© 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. 10-RES-JB
    11. 19018
    Prev
    Next
    INDEX
    Explanations

    phrases related to family members

    oai_token-act-pair · gpt-3.5-turbo

    references to family relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUM
    -0.75
    aly
    -0.71
    oliberal
    -0.70
    Leaks
    -0.70
    AE
    -0.69
    Ĥİ
    -0.69
    Ĥª
    -0.69
     Shape
    -0.66
    metry
    -0.65
     Gutenberg
    -0.65
    POSITIVE LOGITS
     niece
    1.62
     nephew
    1.59
     sister
    1.58
     daughter
    1.53
     sisters
    1.49
     cousin
    1.49
     granddaughter
    1.49
     aunt
    1.46
     cousins
    1.44
     girlfriend
    1.43
    Activations Density 0.094%

    No Known Activations