© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 21611
    Prev
    Next
    INDEX
    Explanations

    locations within a digital interface, specifically focusing on positions within the screen or page

    oai_token-act-pair · gpt-3.5-turbo

    references to the layout and positions of elements on a screen or page

    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
    allo
    -0.66
     virginity
    -0.65
    iji
    -0.62
    ewitness
    -0.61
    uca
    -0.60
    usat
    -0.59
     Pigs
    -0.56
    emale
    -0.56
    oglobin
    -0.55
    Boost
    -0.55
    POSITIVE LOGITS
     corner
    1.23
     toolbar
    1.16
     sidebar
    1.09
    most
    1.02
     pane
    1.00
     panel
    0.99
     menu
    0.97
     left
    0.92
    panel
    0.90
    left
    0.90
    Activations Density 0.074%

    No Known Activations