© 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. 10-RES-JB
    11. 13990
    Prev
    Next
    INDEX
    Explanations

    ages of children

    oai_token-act-pair · gpt-3.5-turbo

    specific numbers related to family structures and children

    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
    zsche
    -0.68
    uncture
    -0.68
    matter
    -0.66
     totality
    -0.65
    detail
    -0.64
     captcha
    -0.63
     obscurity
    -0.63
    rame
    -0.63
     backlash
    -0.62
    statement
    -0.62
    POSITIVE LOGITS
     daughters
    1.75
     sons
    1.60
     grandchildren
    1.52
     siblings
    1.47
     children
    1.31
     sisters
    1.31
     daughter
    1.21
     girlfriends
    1.20
     nephew
    1.18
     kids
    1.16
    Activations Density 0.094%

    No Known Activations