© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 2023
    Prev
    Next
    INDEX
    Explanations

    assorted proper names, likely used in film credits

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and numeric representations, often in contexts related to lists or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uca
    -0.69
     disapp
    -0.66
     scrap
    -0.65
    xual
    -0.64
    pection
    -0.63
    urance
    -0.62
    cius
    -0.62
     governed
    -0.62
    swer
    -0.61
     fluct
    -0.61
    POSITIVE LOGITS
    Synopsis
    0.85
    Legendary
    0.83
    Appearances
    0.82
    Frames
    0.81
    ³³³
    0.80
    Reviewed
    0.79
    ³³³³³³³³³³³³³³³³
    0.78
    Rating
    0.74
    ³³³³
    0.73
    Includes
    0.73
    Activations Density 0.292%

    No Known Activations