© 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. 11-RES-JB
    11. 7466
    Prev
    Next
    INDEX
    Explanations

    specific keyword prompts related to a certain topic or brand called "Op"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Op" followed by a numerically formatted phrase or term

    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
     mileage
    -0.73
     devils
    -0.67
    wagen
    -0.67
     wart
    -0.66
     calves
    -0.63
     reconc
    -0.62
    ãĥīãĥ©ãĤ´ãĥ³
    -0.59
     recall
    -0.58
     confounding
    -0.58
     swear
    -0.55
    POSITIVE LOGITS
    aque
    1.41
    inion
    1.22
    acity
    1.21
    ulence
    1.18
    rah
    1.17
    yright
    1.15
    ener
    1.14
    ulent
    1.12
    iate
    1.09
    osite
    1.08
    Activations Density 0.025%

    No Known Activations