© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11215
    Prev
    Next
    INDEX
    Explanations

    descriptions of buttons or physical controls

    oai_token-act-pair · gpt-3.5-turbo

    descriptive terms related to buttons and their functions on a device

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abama
    -0.94
    Economic
    -0.81
    ulf
    -0.76
    Sal
    -0.75
     Salem
    -0.72
    apeake
    -0.72
    ocaust
    -0.71
     Pension
    -0.71
     Negro
    -0.71
    Financial
    -0.70
    POSITIVE LOGITS
     touchscreen
    1.58
     buttons
    1.35
     removable
    1.23
     toggle
    1.16
     OLED
    1.15
     joystick
    1.14
     menus
    1.13
     headphone
    1.13
     interchangeable
    1.13
     toolbar
    1.12
    Activations Density 0.660%

    No Known Activations