© 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. 229
    Prev
    Next
    INDEX
    Explanations

    references to the season "Spring"

    oai_token-act-pair · gpt-3.5-turbo
    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
    Merit
    -0.71
    endez
    -0.67
     Dign
    -0.67
     Telescope
    -0.66
    ramer
    -0.65
    alcohol
    -0.62
    icate
    -0.62
    ukes
    -0.61
    icated
    -0.61
    egu
    -0.61
    POSITIVE LOGITS
    steen
    1.41
    trap
    1.21
    time
    1.20
    board
    1.20
    boards
    1.08
    Board
    1.02
     semester
    1.01
    meier
    0.96
    tails
    0.95
    fields
    0.94
    Activations Density 0.023%

    No Known Activations