© 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. 11490
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating that something is only a specific thing and nothing more

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate something is merely a superficial or trivial version of something else

    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
    ESE
    -0.89
     PLUS
    -0.85
    YES
    -0.81
    NOW
    -0.77
    cest
    -0.76
     ALSO
    -0.75
     NEVER
    -0.75
    nect
    -0.73
    mediately
    -0.73
    Especially
    -0.72
    POSITIVE LOGITS
     placeholder
    1.05
     incidental
    1.02
     speculation
    0.99
     curiosity
    0.98
     decoration
    0.98
     cosmetic
    0.96
     decorative
    0.94
     anecdotal
    0.92
     coincidence
    0.92
     conjecture
    0.91
    Activations Density 0.334%

    No Known Activations