© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9316
    Prev
    Next
    INDEX
    Explanations

    keywords related to mathematics

    oai_token-act-pair · gpt-3.5-turbo

    references to math and its various contexts within education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sov
    -0.79
    osi
    -0.68
     Parties
    -0.67
    ifest
    -0.65
    ovo
    -0.65
    LEASE
    -0.65
    ————————
    -0.64
    osuke
    -0.64
    views
    -0.64
    essee
    -0.63
    POSITIVE LOGITS
    matical
    1.06
     equations
    0.90
     algebra
    0.86
    mers
    0.86
    gebra
    0.84
    enza
    0.82
    hematic
    0.81
     math
    0.81
    ilda
    0.80
    hemat
    0.80
    Activations Density 0.020%

    No Known Activations