© 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. 9-RES-JB
    11. 4307
    Prev
    Next
    INDEX
    Explanations

    proper nouns signifying entities like organizations or people

    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
     organisms
    -0.70
    Avoid
    -0.66
    Enjoy
    -0.66
    Merit
    -0.63
    Evil
    -0.63
    Autom
    -0.62
    frames
    -0.61
     creeps
    -0.61
    Arcade
    -0.61
    CHAPTER
    -0.60
    POSITIVE LOGITS
     spokeswoman
    1.41
     spokesman
    1.39
     spokesperson
    1.36
    cknowled
    1.16
     representative
    0.99
    gency
    0.99
     statement
    0.99
    ctors
    0.93
    uckland
    0.89
    mber
    0.89
    Activations Density 0.166%

    No Known Activations