© 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. 7-RES-JB
    11. 13772
    Prev
    Next
    INDEX
    Explanations

    references to family members such as parents, mom, dad, auntie, etc

    oai_token-act-pair · gpt-3.5-turbo

    references to familial terms and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jriwal
    -0.93
    ibrary
    -0.92
     fram
    -0.73
    rawdownloadcloneembedreportprint
    -0.72
    nesota
    -0.69
    chnology
    -0.68
     judiciary
    -0.66
    urgical
    -0.65
     reservoirs
    -0.64
    icter
    -0.63
    POSITIVE LOGITS
     Daddy
    1.11
     Mama
    0.96
    addy
    0.95
    hood
    0.95
     Daughter
    0.93
     Claus
    0.91
     daddy
    0.90
    cake
    0.89
    Daddy
    0.88
     Cookie
    0.88
    Activations Density 0.088%

    No Known Activations