© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 17294
    Prev
    Next
    INDEX
    Explanations

    financial and regulatory terms and words related to law and governance

    oai_token-act-pair · gpt-3.5-turbo

    references to specific organizations, policies, or entities related to governance and societal structures

    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
    Negative Logits
    etheless
    -0.70
     vain
    -0.64
    terday
    -0.59
    WAYS
    -0.58
    utics
    -0.56
    anwhile
    -0.56
     convincing
    -0.55
    ĻĤ
    -0.55
    doms
    -0.53
    Downloadha
    -0.53
    POSITIVE LOGITS
     Room
    0.84
     Consortium
    0.73
     Registry
    0.72
     Factor
    0.72
     Advisory
    0.72
     Committee
    0.71
     Quarter
    0.71
     Initiative
    0.71
     Services
    0.70
     Club
    0.70
    Activations Density 0.773%

    No Known Activations