© 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. 8-RES-JB
    11. 11128
    Prev
    Next
    INDEX
    Explanations

    references to specific time periods, particularly the term "Century."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific centuries, primarily the 20th and 21st centuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uala
    -0.96
    etsk
    -0.96
    oaded
    -0.88
     sqor
    -0.82
    ogy
    -0.81
    edin
    -0.79
    toc
    -0.77
    staking
    -0.77
    govtrack
    -0.76
    onen
    -0.75
    POSITIVE LOGITS
     Fox
    0.87
     Century
    0.85
     Vision
    0.80
     Views
    0.78
     Weaver
    0.77
     Edison
    0.75
     Heritage
    0.72
     Falcon
    0.72
     Earth
    0.71
     Aviation
    0.69
    Activations Density 0.038%

    No Known Activations