© 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. 15484
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "Single Payer" in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to a specific gameplay or strategy, focusing on the term "Single Player."

    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
     ambassadors
    -0.71
     fres
    -0.69
     riot
    -0.68
     pir
    -0.67
     dred
    -0.66
    ghazi
    -0.65
     gar
    -0.65
    gur
    -0.65
     fortune
    -0.64
     marsh
    -0.64
    POSITIVE LOGITS
     Single
    3.21
    Single
    2.50
    single
    1.66
    Multi
    1.42
     Multi
    1.22
     Married
    1.22
     Individual
    1.21
     Dual
    1.18
     Multiple
    1.13
     Female
    1.09
    Activations Density 0.029%

    No Known Activations