© 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. 9624
    Prev
    Next
    INDEX
    Explanations

    mentions of time periods or eras

    oai_token-act-pair · gpt-3.5-turbo
    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
    acted
    -0.86
    acts
    -0.86
    emort
    -0.84
    Leaks
    -0.75
    ACTED
    -0.71
    iscopal
    -0.69
    Materials
    -0.68
    edly
    -0.68
    ãĥ´ãĤ¡
    -0.68
    Reviewed
    -0.67
    POSITIVE LOGITS
    pring
    1.15
    creen
    0.99
    hift
    0.98
    cale
    0.90
    dream
    0.85
    cript
    0.79
    laus
    0.79
    mith
    0.78
    pread
    0.73
    amoto
    0.70
    Activations Density 0.039%

    No Known Activations