© 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. 1-RES-JB
    11. 22021
    Prev
    Next
    INDEX
    Explanations

    words related to dynasties or long-lasting power structures

    oai_token-act-pair · gpt-3.5-turbo

    references to dynasties and hereditary systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    horn
    -0.76
    ãĥ¤
    -0.76
    matter
    -0.75
     Ker
    -0.73
    GO
    -0.70
     Stim
    -0.68
    rd
    -0.67
     Staff
    -0.67
    CV
    -0.67
    eret
    -0.66
    POSITIVE LOGITS
     dynasty
    1.46
     dyn
    1.22
    ynasty
    1.05
     Dynasty
    0.92
    interstitial
    0.85
     monarchy
    0.83
     tyr
    0.82
     resil
    0.78
     millenn
    0.77
    ilial
    0.76
    Activations Density 0.010%

    No Known Activations