© 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 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. 0-RES-JB
    11. 12686
    Prev
    Next
    INDEX
    Explanations

    references to memorials or commemorations

    oai_token-act-pair · gpt-3.5-turbo

    references to memorials and commemoration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Squ
    -0.68
     Flex
    -0.68
    drive
    -0.67
    wise
    -0.67
     coefficients
    -0.66
    strap
    -0.66
    pressure
    -0.63
    ãĢį
    -0.63
    drivers
    -0.63
    ource
    -0.63
    POSITIVE LOGITS
     memorial
    3.72
     Memorial
    2.14
     remembrance
    1.99
     commem
    1.94
     commemor
    1.93
     monument
    1.81
     funeral
    1.70
     monuments
    1.64
     tribute
    1.63
     vigil
    1.55
    Activations Density 0.012%

    No Known Activations