© 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. 20966
    Prev
    Next
    INDEX
    Explanations

    instances of the word "shift" with high relevance

    oai_token-act-pair · gpt-3.5-turbo

    references to significant changes or transformations

    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
     Seym
    -0.67
     Godd
    -0.61
    lov
    -0.61
    ÄŁ
    -0.61
    ortium
    -0.60
    Interstitial
    -0.60
    gom
    -0.60
     Smile
    -0.60
    REDACTED
    -0.60
    CRIP
    -0.59
    POSITIVE LOGITS
     gears
    1.27
     toward
    1.01
     blame
    1.01
     towards
    0.97
     away
    0.95
     sands
    0.95
     shift
    0.90
    iness
    0.85
     shifts
    0.80
     downwards
    0.79
    Activations Density 0.064%

    No Known Activations