© 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. 7-RES-JB
    11. 14100
    Prev
    Next
    INDEX
    Explanations

    words related to legal terms and regulations

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the need for clarity or decisiveness in discussions related to freedom and regulation

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    EStream
    -0.91
    kees
    -0.87
    swick
    -0.84
    owler
    -0.77
    RPG
    -0.73
    hov
    -0.72
    ojure
    -0.71
    wright
    -0.71
    eah
    -0.70
    ods
    -0.70
    POSITIVE LOGITS
     unamb
    1.02
     unbiased
    0.97
    rogen
    0.94
     effective
    0.92
     consistent
    0.90
     undeniable
    0.90
     unequiv
    0.89
     trustworthy
    0.89
     unconditional
    0.88
     proven
    0.88
    Activations Density 0.199%

    No Known Activations