© 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. 4268
    Prev
    Next
    INDEX
    Explanations

    references to producers in film and television credits

    oai_token-act-pair · gpt-3.5-turbo
    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
    MpServer
    -0.82
    ibaba
    -0.79
    ties
    -0.77
    ocene
    -0.69
    bia
    -0.69
    mia
    -0.68
    carry
    -0.68
    unin
    -0.67
    Leader
    -0.65
    ndum
    -0.64
    POSITIVE LOGITS
     extraord
    1.00
     Steven
    0.94
     Gareth
    0.93
     Constantin
    0.90
     Zack
    0.85
     Aaron
    0.82
     Todd
    0.82
     Damien
    0.81
     Quentin
    0.80
     Alan
    0.80
    Activations Density 0.117%

    No Known Activations