© 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. 12075
    Prev
    Next
    INDEX
    Explanations

    words related to scientific studies and research findings

    oai_token-act-pair · gpt-3.5-turbo

    scientific studies and findings related to health and behavior

    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
    Disclaimer
    -0.92
    istries
    -0.80
    Ô
    -0.77
    NOW
    -0.66
    APTER
    -0.63
    Pur
    -0.62
     Obst
    -0.61
     Hopefully
    -0.61
    çīĪ
    -0.60
    aye
    -0.60
    POSITIVE LOGITS
     correlated
    1.12
     improves
    1.06
     differed
    1.05
     induces
    1.03
     outper
    1.03
     decreases
    1.02
     fared
    1.01
     correlates
    1.00
     significantly
    1.00
     predicts
    0.99
    Activations Density 0.375%

    No Known Activations