© 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. 2945
    Prev
    Next
    INDEX
    Explanations

    technical terms in computing and programming

    oai_token-act-pair · gpt-3.5-turbo

    terms related to collections and classifications of items or concepts

    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
    HOME
    -0.61
     Tsukuyomi
    -0.54
     Governors
    -0.53
     Sutherland
    -0.51
     Victory
    -0.50
     Commissioners
    -0.48
     insider
    -0.48
     Apostle
    -0.47
     calculus
    -0.47
     Guid
    -0.47
    POSITIVE LOGITS
    alysed
    1.11
    ivated
    1.09
    antly
    1.08
    ibly
    1.06
    iably
    1.05
    elled
    1.03
    etically
    1.02
    inated
    1.01
    ited
    1.01
    alled
    1.01
    Activations Density 0.416%

    No Known Activations