© 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. 7537
    Prev
    Next
    INDEX
    Explanations

    math-related terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to mathematical concepts and terms

    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
    essee
    -0.66
    oway
    -0.64
     Luxem
    -0.63
    ————————
    -0.63
     Sheridan
    -0.61
    utsche
    -0.61
     Sov
    -0.60
    lights
    -0.60
    felt
    -0.60
    IDA
    -0.60
    POSITIVE LOGITS
    matical
    1.22
     equations
    1.08
    ilde
    1.02
    hematic
    0.97
    letes
    0.93
    ilda
    0.90
     equation
    0.88
     homework
    0.87
    hemat
    0.83
     formulas
    0.83
    Activations Density 0.080%

    No Known Activations