© 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. 9-RES-JB
    11. 20790
    Prev
    Next
    INDEX
    Explanations

    instances where a comparison is made between different entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "that"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lin
    -0.76
    izont
    -0.76
    ormons
    -0.76
    istors
    -0.75
    istor
    -0.73
    events
    -0.73
    stals
    -0.71
    adia
    -0.70
    apolis
    -0.70
    initely
    -0.69
    POSITIVE LOGITS
     fateful
    1.20
     pesky
    0.96
     portion
    0.91
    cher
    0.90
     elusive
    0.90
     aspect
    0.85
     same
    0.81
     notion
    0.79
    chery
    0.78
    ched
    0.76
    Activations Density 0.217%

    No Known Activations