© 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. 10075
    Prev
    Next
    INDEX
    Explanations

    family relationships, specifically between parents and their children

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks indicating pauses or breaks in sentences

    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
    etary
    -0.77
    imize
    -0.76
    wcs
    -0.75
    medi
    -0.73
    EngineDebug
    -0.72
    "]=>
    -0.71
    printf
    -0.70
    Topic
    -0.70
    cffffcc
    -0.69
    CONCLUS
    -0.69
    POSITIVE LOGITS
     grandson
    1.03
     nephew
    1.01
     Nathan
    1.01
     Buddy
    1.00
     brother
    0.99
     Sammy
    0.99
     Marvin
    0.99
     Melvin
    0.98
     Nathaniel
    0.98
     Tammy
    0.98
    Activations Density 0.099%

    No Known Activations