© 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. 21969
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical processes like "transport," "mixing," and "evaporator."

    oai_token-act-pair · gpt-3.5-turbo

    processes and actions related to physical properties and transformations of materials

    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
     Journalism
    -0.68
     Liberal
    -0.63
     DACA
    -0.62
     Citizenship
    -0.62
     LGBT
    -0.61
     Saudi
    -0.59
    èĢħ
    -0.59
     Socialist
    -0.59
     Cosponsors
    -0.59
    Liberal
    -0.59
    POSITIVE LOGITS
     moisture
    0.72
     hardness
    0.71
     protr
    0.71
     compact
    0.70
     surface
    0.70
     dehyd
    0.70
     thickness
    0.70
     electrons
    0.69
     texture
    0.69
     elong
    0.68
    Activations Density 2.946%

    No Known Activations