© 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. 7-RES-JB
    11. 1788
    Prev
    Next
    INDEX
    Explanations

    institution names or references to a specific university

    oai_token-act-pair · gpt-3.5-turbo

    references to rice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istically
    -0.87
    istical
    -0.79
    ufact
    -0.77
    acular
    -0.76
    raviolet
    -0.75
    merce
    -0.75
    ileaks
    -0.73
    oulder
    -0.71
    anza
    -0.71
    destruct
    -0.69
    POSITIVE LOGITS
     cooker
    1.06
    cloth
    0.90
    washer
    0.87
     Rice
    0.77
     cakes
    0.77
     Kris
    0.77
    cook
    0.76
    bowl
    0.76
    ption
    0.74
     bowls
    0.74
    Activations Density 0.026%

    No Known Activations