© 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 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. 4-RES-JB
    11. 4821
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "menu"

    oai_token-act-pair · gpt-3.5-turbo

    references to menus or menu options

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

    No Comments

    Negative Logits
    女
    -0.80
     Sidd
    -0.71
    esville
    -0.65
     Fundamental
    -0.65
    ioxide
    -0.65
    theless
    -0.64
     Mary
    -0.63
     Wyatt
    -0.62
     Archangel
    -0.62
     Coy
    -0.61
    POSITIVE LOGITS
    entry
    0.98
    isine
    0.94
    cloth
    0.90
     menu
    0.88
     options
    0.87
     menus
    0.86
    eteria
    0.85
    ande
    0.83
    ropri
    0.81
     choices
    0.81
    Activations Density 0.014%

    No Known Activations