© 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. 2-RES-JB
    11. 12700
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, specifically focusing on the name "Trey"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals named Trey and thematic elements related to trips and tales

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elaide
    -0.78
    initions
    -0.77
    manship
    -0.73
    foundland
    -0.73
    CLUD
    -0.72
    ials
    -0.70
    soDeliveryDate
    -0.68
    nesota
    -0.68
    utive
    -0.67
    paces
    -0.67
    POSITIVE LOGITS
    von
    0.88
     Remastered
    0.82
     Desk
    0.80
    Pros
    0.78
     Rez
    0.75
     Tours
    0.74
    ologic
    0.74
     Rapp
    0.74
     Tavern
    0.73
    Nap
    0.71
    Activations Density 0.021%

    No Known Activations