© 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. 10-RES-JB
    11. 3264
    Prev
    Next
    INDEX
    Explanations

    scientific terms, such as specific phenomena or concepts described in different fields

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scientific phenomena and definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mails
    -0.72
    uffs
    -0.71
    iddles
    -0.71
    ighty
    -0.67
    Items
    -0.66
    SPONSORED
    -0.66
    araoh
    -0.65
     dstg
    -0.65
    -------------
    -0.62
    arnaev
    -0.61
    POSITIVE LOGITS
     "
    0.94
     '
    0.82
     "(
    0.79
     tert
    0.76
     ``
    0.74
     "#
    0.74
     "'
    0.72
     gluc
    0.72
     Phase
    0.71
     "\
    0.71
    Activations Density 0.091%

    No Known Activations