© 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. 15884
    Prev
    Next
    INDEX
    Explanations

    information related to scientific elements and composition

    oai_token-act-pair · gpt-3.5-turbo

    technical and scientific terminology related to chemical composition and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Fix
    -0.82
     Nope
    -0.73
    Yep
    -0.72
    didn
    -0.72
     giveaway
    -0.70
    Deal
    -0.67
    Hunt
    -0.67
     bumped
    -0.66
     Cancel
    -0.66
    Friday
    -0.65
    POSITIVE LOGITS
    Contents
    1.02
     Examples
    1.01
     mammalian
    0.97
     commonly
    0.97
     diverse
    0.95
     anthrop
    0.94
     terminology
    0.94
     encompasses
    0.93
     relational
    0.93
     practitioners
    0.93
    Activations Density 0.880%

    No Known Activations