© 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. 12191
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal or political significance

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and auxiliary verbs indicating continuity and consistency

    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
     Mechdragon
    -0.64
     Towers
    -0.62
    pert
    -0.61
     dust
    -0.59
    frog
    -0.57
     dice
    -0.56
     Loft
    -0.55
     mound
    -0.55
     fry
    -0.54
     Sunder
    -0.54
    POSITIVE LOGITS
     remains
    1.05
     always
    1.03
     continues
    1.01
     ALWAYS
    1.00
     remain
    0.92
    always
    0.90
     forever
    0.88
     still
    0.88
     continue
    0.86
    still
    0.83
    Activations Density 0.091%

    No Known Activations