© 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. 2321
    Prev
    Next
    INDEX
    Explanations

    proper names or names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Walter."

    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
    ebook
    -0.86
    arians
    -0.84
    arian
    -0.83
    naire
    -0.77
    alty
    -0.75
    ally
    -0.75
    expr
    -0.74
    ors
    -0.71
    ional
    -0.71
    ancers
    -0.70
    POSITIVE LOGITS
     Winc
    1.09
     Mond
    1.08
     Payton
    0.98
     Cron
    0.95
     Reed
    0.91
     Io
    0.90
     Isaac
    0.89
     Matth
    0.89
     Sob
    0.88
     Herz
    0.86
    Activations Density 0.032%

    No Known Activations