© 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. 3-RES-JB
    11. 15564
    Prev
    Next
    INDEX
    Explanations

    references to a specific entity named "Vox."

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Vox" and related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    strip
    -0.72
    ipal
    -0.66
    cock
    -0.64
     nudity
    -0.63
    avage
    -0.62
     moons
    -0.62
    draw
    -0.62
    byss
    -0.61
    atham
    -0.60
    ategy
    -0.60
    POSITIVE LOGITS
     Vox
    1.05
     Machina
    0.90
     Emin
    0.81
    istani
    0.79
    NV
    0.77
    enza
    0.72
     Printed
    0.72
    lar
    0.71
     NV
    0.70
    PRESS
    0.69
    Activations Density 0.013%

    No Known Activations