© 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. 4-RES-JB
    11. 20671
    Prev
    Next
    INDEX
    Explanations

    technical and construction-related terms

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of structures and their arrangements

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

    No Comments

    Negative Logits
     Accountability
    -0.63
     Journalism
    -0.62
     Markets
    -0.58
     taxpayer
    -0.58
     Libertarian
    -0.58
    Politics
    -0.58
     Founding
    -0.57
    funding
    -0.57
    Asset
    -0.57
     Criminal
    -0.57
    POSITIVE LOGITS
     protr
    0.83
     elong
    0.80
     diagonal
    0.74
     stationary
    0.71
     angled
    0.69
     alternating
    0.69
     perpendicular
    0.68
     gradient
    0.67
     removable
    0.67
     dorsal
    0.67
    Activations Density 2.967%

    No Known Activations