© 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. 11-RES-JB
    11. 14993
    Prev
    Next
    INDEX
    Explanations

    terms related to economic policies, especially those related to free markets

    oai_token-act-pair · gpt-3.5-turbo

    references to free market concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Archdemon
    -0.79
     Tycoon
    -0.72
     Mits
    -0.69
     Reconstruction
    -0.69
     Miko
    -0.68
     Origins
    -0.67
     Zucker
    -0.65
     Meteor
    -0.65
     Jenner
    -0.65
     Wonderland
    -0.65
    POSITIVE LOGITS
    spir
    1.40
    speech
    1.38
    lance
    1.35
    agent
    1.34
    agency
    1.29
    flo
    1.27
    trade
    1.24
    rider
    1.23
    float
    1.22
    ranging
    1.21
    Activations Density 0.021%

    No Known Activations