© 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. 9-RES-JB
    11. 23587
    Prev
    Next
    INDEX
    Explanations

    the sequence "Wh" followed by other letters like "ore", "ispers", or "arton"

    oai_token-act-pair · gpt-3.5-turbo

    the repeated occurrence of the substring "Wh" across various contexts, indicating a focus on that particular sequence of characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grande
    -0.73
     Duo
    -0.68
     mosaic
    -0.68
     theirs
    -0.63
    steen
    -0.63
     Awakening
    -0.63
     Gou
    -0.62
    ULAR
    -0.61
     expressing
    -0.60
     Letter
    -0.60
    POSITIVE LOGITS
    istle
    1.48
    irlwind
    1.33
    irling
    1.29
    ispers
    1.26
    ilst
    1.25
    irl
    1.21
    ichever
    1.20
    olen
    1.20
    arton
    1.19
    ipl
    1.17
    Activations Density 0.034%

    No Known Activations