© 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. 0-RES-JB
    11. 5118
    Prev
    Next
    INDEX
    Explanations

    terms related to tiling and home improvement, specifically focusing on actions and materials related to tiling

    oai_token-act-pair · gpt-3.5-turbo

    references to tiles in various contexts, particularly in relation to applications and installations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kra
    -0.89
    abol
    -0.77
     Benson
    -0.76
     Chavez
    -0.76
     Kier
    -0.75
     Suicide
    -0.72
    Hug
    -0.70
     Bauer
    -0.70
    olesterol
    -0.67
    avez
    -0.67
    POSITIVE LOGITS
     tiles
    3.62
     tile
    3.60
     Tile
    2.87
    tile
    2.25
    Tile
    2.22
     wallpaper
    1.67
     mosaic
    1.61
     mosa
    1.52
     marble
    1.33
     mats
    1.17
    Activations Density 0.027%

    No Known Activations