© 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 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. 2259
    Prev
    Next
    INDEX
    Explanations

    phrases describing people based on their age and physical state

    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
    ernels
    -1.03
    Frames
    -0.99
    thumbnails
    -0.97
    stocks
    -0.92
     havens
    -0.91
    sites
    -0.90
    units
    -0.88
    apps
    -0.88
     decks
    -0.88
    ships
    -0.87
    POSITIVE LOGITS
     woman
    1.58
     classmate
    1.26
     girl
    1.22
     colleague
    1.21
     female
    1.16
     man
    1.16
     couple
    1.15
     staffer
    1.14
     lady
    1.10
     protester
    1.08
    Activations Density 0.170%

    No Known Activations