© 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. 9651
    Prev
    Next
    INDEX
    Explanations

    terms related to health and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    the word "can" in various contexts

    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
     Fighter
    -0.68
     Quarter
    -0.63
     honoring
    -0.63
     striving
    -0.62
     competitor
    -0.62
     Fighting
    -0.62
     BAL
    -0.61
     Seeking
    -0.61
     Moz
    -0.60
     Mant
    -0.59
    POSITIVE LOGITS
    't
    1.57
    berra
    1.23
    adian
    1.22
    isters
    1.11
    NOT
    1.04
    ister
    1.04
     afford
    0.94
     easily
    0.92
    vas
    0.91
     attest
    0.90
    Activations Density 0.174%

    No Known Activations