© 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. 3316
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers with hyphens, such as "once 10-unthinkable" and "once 8-"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to repeated situations or conditions, particularly those indicating frequency or prior occurrences

    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
     Shutterstock
    -0.78
    ĺħ
    -0.76
    eday
    -0.73
     Females
    -0.72
    ODY
    -0.71
     RELEASE
    -0.70
     Rider
    -0.67
    ongyang
    -0.66
     Tags
    -0.66
    arella
    -0.64
    POSITIVE LOGITS
     insur
    1.03
     pristine
    1.00
     meager
    0.97
     shaky
    0.96
     insignificant
    0.96
     unstoppable
    0.95
     inexplicable
    0.95
     chaotic
    0.95
     illustrious
    0.94
     dismal
    0.94
    Activations Density 0.125%

    No Known Activations