© 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. 8199
    Prev
    Next
    INDEX
    Explanations

    phrases related to user interactions with technology or software systems

    oai_token-act-pair · gpt-3.5-turbo

    user interactions and user experiences within digital interfaces

    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
    åħī
    -1.02
    punk
    -0.75
     kits
    -0.70
    wives
    -0.67
     feud
    -0.66
    ylum
    -0.66
     fost
    -0.66
     characterization
    -0.65
    hospital
    -0.64
    oust
    -0.62
    POSITIVE LOGITS
     clicked
    1.62
     clicking
    1.45
     scroll
    1.45
     login
    1.42
     click
    1.42
     Ctrl
    1.35
     CTRL
    1.33
     clicks
    1.33
     scrolling
    1.32
     swipe
    1.27
    Activations Density 0.377%

    No Known Activations