Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 1717
    Prev
    Next
    INDEX
    Explanations

    terms related to computer menus and options

    oai_token-act-pair · gpt-3.5-turbo

    references to various menu items and options within a user interface

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ioxide
    -0.82
    女
    -0.79
     Marketable
    -0.71
    6666
    -0.70
    theless
    -0.70
    esville
    -0.67
     Chatt
    -0.67
    ships
    -0.66
     Rachel
    -0.66
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.66
    POSITIVE LOGITS
    entry
    0.96
     drawer
    0.86
     menu
    0.83
    cloth
    0.83
     options
    0.83
    uration
    0.78
    menu
    0.77
     menus
    0.75
    eteria
    0.74
    plate
    0.73
    Activations Density 0.017%

    No Known Activations