© 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. 1-RES-JB
    11. 3405
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to names, especially the name "Pat"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Pat" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vous
    -0.96
    shapeshifter
    -0.81
    ;;;;;;;;;;;;
    -0.76
    ãĤ¼ãĤ¦ãĤ¹
    -0.75
    hower
    -0.72
    PRES
    -0.69
     Afric
    -0.69
    STD
    -0.69
     Abyssal
    -0.68
    perse
    -0.66
    POSITIVE LOGITS
    ients
    0.96
    terson
    0.95
     Pat
    0.94
    ricks
    0.92
    ented
    0.92
    riots
    0.91
    ikarp
    0.91
    ament
    0.90
    ricia
    0.89
    utations
    0.88
    Activations Density 0.009%

    No Known Activations