© 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. 20802
    Prev
    Next
    INDEX
    Explanations

    instances where an action was completed or accomplished

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "It took" indicating duration or effort

    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
    è¦ļéĨĴ
    -0.86
    luaj
    -0.78
    ãĤ¦ãĤ¹
    -0.71
    uclear
    -0.70
    Americ
    -0.68
    ranch
    -0.67
    çļ
    -0.65
    ionic
    -0.64
    MAP
    -0.64
    aghd
    -0.64
    POSITIVE LOGITS
     awhile
    1.38
     longer
    1.08
     months
    1.02
     years
    1.00
     decades
    1.00
     precedence
    0.96
     ages
    0.95
     forever
    0.93
     weeks
    0.93
     place
    0.92
    Activations Density 0.039%

    No Known Activations