© 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. 11-RES-JB
    11. 20999
    Prev
    Next
    INDEX
    Explanations

    words related to drawing conclusions or summarizing findings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "conclude" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assetsadobe
    -0.68
    loads
    -0.64
    RN
    -0.62
    dos
    -0.62
    gren
    -0.61
    lease
    -0.61
    isters
    -0.60
    enf
    -0.60
    tan
    -0.60
    eni
    -0.58
    POSITIVE LOGITS
     concluding
    0.86
     conclusions
    0.79
     conclusion
    0.79
     that
    0.77
     unanimously
    0.73
     conclude
    0.70
    iture
    0.70
    atively
    0.68
     based
    0.68
    itures
    0.67
    Activations Density 0.052%

    No Known Activations