© 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. 9-RES-JB
    11. 11387
    Prev
    Next
    INDEX
    Explanations

    phrases related to revealing information, especially plot twists and spoilers

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to habits and routines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ayne
    -0.69
    hran
    -0.69
    apore
    -0.69
    lez
    -0.69
    english
    -0.66
    >>
    -0.66
     tonight
    -0.64
    greg
    -0.64
    çīĪ
    -0.63
    chell
    -0.61
    POSITIVE LOGITS
     underdog
    0.97
     unve
    0.87
     oneself
    0.85
     unexpected
    0.85
     stumble
    0.85
     headline
    0.78
     hastily
    0.77
     triumph
    0.76
     unexpectedly
    0.75
     suddenly
    0.73
    Activations Density 1.222%

    No Known Activations