© 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. 11-RES-JB
    11. 22362
    Prev
    Next
    INDEX
    Explanations

    mentions related to a particular person named Treon Harris

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals and their related attributes or actions

    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
    Å
    -1.00
     Velvet
    -0.96
    Tai
    -0.91
     Simpsons
    -0.88
     Simpson
    -0.86
    Yang
    -0.86
     Vim
    -0.82
    virt
    -0.81
     Coco
    -0.81
     exported
    -0.80
    POSITIVE LOGITS
     Harris
    2.77
    Harris
    2.72
     Carr
    1.37
     Houston
    1.23
     Hath
    1.17
     Levi
    1.17
    Houston
    1.15
     Perkins
    1.13
     Garr
    1.13
     Sixers
    1.08
    Activations Density 0.185%

    No Known Activations