© 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. 11429
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant events or developments

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "the."

    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
    hower
    -0.60
    properties
    -0.57
    ela
    -0.56
     ______
    -0.56
    milo
    -0.56
     Returns
    -0.55
    slave
    -0.54
    verning
    -0.53
    hak
    -0.53
    haw
    -0.53
    POSITIVE LOGITS
     largest
    1.12
     possibility
    1.07
     biggest
    1.02
     brunt
    1.01
     toughest
    0.99
     longest
    0.98
     heaviest
    0.97
     deadliest
    0.97
     beginnings
    0.96
     slightest
    0.95
    Activations Density 0.328%

    No Known Activations