© 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. 2-RES-JB
    11. 12590
    Prev
    Next
    INDEX
    Explanations

    calculations or mathematical formulas

    oai_token-act-pair · gpt-3.5-turbo

    references to mathematical or logical formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usters
    -0.71
     Intellectual
    -0.65
    hu
    -0.64
    ividual
    -0.64
     Gri
    -0.62
    adder
    -0.62
     Hearing
    -0.62
     Printed
    -0.62
    ulhu
    -0.61
     Mariners
    -0.60
    POSITIVE LOGITS
     formula
    1.37
     formulas
    1.19
     formulation
    0.77
     Formula
    0.71
     formulations
    0.71
     equation
    0.70
     notation
    0.69
    rition
    0.69
     equations
    0.66
     withd
    0.66
    Activations Density 0.008%

    No Known Activations