© 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. 6-RES-JB
    11. 5042
    Prev
    Next
    INDEX
    Explanations

    medical abbreviations and terms related to anatomy and physiology

    oai_token-act-pair · gpt-3.5-turbo

    references to LSU (Louisiana State University) and related identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stoked
    -0.71
    legates
    -0.70
    natal
    -0.66
    icz
    -0.61
    faces
    -0.58
    swer
    -0.58
    emaker
    -0.57
    strate
    -0.57
     infant
    -0.57
     living
    -0.56
    POSITIVE LOGITS
    aturday
    1.00
    heed
    0.94
    gow
    0.93
    ibrary
    0.89
    ued
    0.88
    aturdays
    0.88
    earch
    0.84
    ovie
    0.81
    oyd
    0.81
    OCK
    0.78
    Activations Density 0.039%

    No Known Activations