© 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. 17494
    Prev
    Next
    INDEX
    Explanations

    dates in the format day-month-year

    oai_token-act-pair · gpt-3.5-turbo

    date references or numerical values

    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
    ophon
    -0.75
    otle
    -0.67
    anol
    -0.64
    allo
    -0.62
    aleb
    -0.61
    ype
    -0.61
    atis
    -0.61
    atically
    -0.60
    fare
    -0.60
    ĸļ
    -0.60
    POSITIVE LOGITS
    00
    1.36
    th
    1.15
    50
    0.99
    nm
    0.95
    60
    0.94
    01
    0.89
    %-
    0.85
    isher
    0.85
    %
    0.85
    000
    0.85
    Activations Density 0.158%

    No Known Activations