© 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. 11-RES-JB
    11. 20581
    Prev
    Next
    INDEX
    Explanations

    words related to physical structures, specifically floors

    oai_token-act-pair · gpt-3.5-turbo

    references to different types and features of floors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ega
    -0.83
    elson
    -0.71
    ague
    -0.69
    lez
    -0.69
    ño
    -0.68
     ALS
    -0.66
    opia
    -0.64
    eday
    -0.64
    NULL
    -0.64
     Mandela
    -0.64
    POSITIVE LOGITS
    boards
    1.34
    plan
    1.06
     mats
    1.03
    nuts
    1.01
    floor
    0.98
    pace
    0.96
     tiles
    0.95
    flo
    0.93
     floor
    0.91
    nut
    0.91
    Activations Density 0.055%

    No Known Activations