© 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. 7527
    Prev
    Next
    INDEX
    Explanations

    dates and times mentioned in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    temporal references and dates

    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
    MF
    -0.78
    Hart
    -0.77
    KING
    -0.76
    SL
    -0.73
    elson
    -0.73
    TEXTURE
    -0.72
    agnetic
    -0.72
    ady
    -0.72
    AF
    -0.71
    AFTA
    -0.71
    POSITIVE LOGITS
     Dec
    2.48
     Nov
    2.12
     Oct
    2.12
    Dec
    2.01
     Jan
    1.92
     Sep
    1.90
     Feb
    1.88
    Nov
    1.87
     Aug
    1.82
     Apr
    1.82
    Activations Density 0.067%

    No Known Activations