© 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. 11318
    Prev
    Next
    INDEX
    Explanations

    optimal performance descriptions or evaluations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "this"

    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
    oller
    -0.85
    krit
    -0.74
    jew
    -0.72
    uality
    -0.71
    facts
    -0.68
    papers
    -0.65
    edu
    -0.63
    conom
    -0.62
    ا
    -0.61
    vich
    -0.61
    POSITIVE LOGITS
     season
    1.26
     offseason
    1.21
     year
    1.10
     weekend
    1.08
     matchup
    1.07
     week
    1.01
     preseason
    0.99
     postseason
    0.98
     squad
    0.93
     backfield
    0.90
    Activations Density 0.110%

    No Known Activations