© 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. 0-RES-JB
    11. 5278
    Prev
    Next
    INDEX
    Explanations

    names of a specific person, especially Leanne

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly "Leanne" and "Lore."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Winged
    -0.90
     ts
    -0.75
    hib
    -0.71
     Yak
    -0.68
     dash
    -0.68
    ãĤ¨ãĥ«
    -0.68
     Ki
    -0.64
     Inferno
    -0.63
    ãĥĩ
    -0.63
     leaf
    -0.63
    POSITIVE LOGITS
    anne
    2.29
     Summers
    1.68
    adh
    1.50
     Lore
    1.50
    ellen
    1.49
     Nicole
    1.37
    anza
    1.27
    bye
    1.22
    addafi
    1.09
    iem
    1.07
    Activations Density 0.044%

    No Known Activations