© 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. 2-RES-JB
    11. 3190
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or political concepts, specifically the separation of powers or church and state

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of separation, particularly regarding the separation of powers and church and state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.71
    TL
    -0.67
     Hels
    -0.66
    herty
    -0.66
    yrics
    -0.65
     Prospect
    -0.64
    ×Ķ
    -0.64
    0000000000000000
    -0.62
     Revelations
    -0.62
    example
    -0.62
    POSITIVE LOGITS
     separation
    1.22
     separ
    0.91
    separ
    0.88
     separating
    0.82
    aration
    0.79
     separated
    0.79
     headaches
    0.75
     boundaries
    0.74
     pits
    0.74
     barriers
    0.74
    Activations Density 0.011%

    No Known Activations