© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 11337
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically referencing the name "TON"

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the term "TON" in various contexts

    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
     fle
    -0.68
     Pur
    -0.66
     stray
    -0.66
     similarly
    -0.63
     Dre
    -0.63
     Breach
    -0.63
     Fate
    -0.62
     Esp
    -0.62
     Bas
    -0.60
     rescue
    -0.60
    POSITIVE LOGITS
    TON
    4.72
    tons
    1.63
    ton
    1.41
    INGTON
    1.34
    WOOD
    1.26
    SON
    1.20
    PER
    1.13
    TY
    1.12
    RON
    1.11
    BILL
    1.08
    Activations Density 0.023%

    No Known Activations