© 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. 7837
    Prev
    Next
    INDEX
    Explanations

    text with the word "Your" followed by a capitalized noun, potentially focusing on personalized content

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Your"

    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
    models
    -0.73
    itud
    -0.70
    forth
    -0.69
    ality
    -0.67
    hunt
    -0.66
     airs
    -0.66
    daq
    -0.65
    verb
    -0.65
    xxx
    -0.62
    pher
    -0.62
    POSITIVE LOGITS
     mileage
    1.16
     browser
    1.12
     favorite
    1.00
     favourite
    0.97
     Favorite
    0.95
     Browser
    0.94
     complimentary
    0.89
    selves
    0.85
     correspondent
    0.85
     imagination
    0.80
    Activations Density 0.078%

    No Known Activations