© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18022
    Prev
    Next
    INDEX
    Explanations

    references or mentions of titles, positions, or entities related to authority, such as 'lord'

    oai_token-act-pair · gpt-3.5-turbo

    references to "lords," particularly in various contexts such as drug lords, feudal lords, and authority figures

    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
    issance
    -0.82
     Devils
    -0.79
    anuts
    -0.74
    jam
    -0.73
    jee
    -0.72
    uting
    -0.70
     Trees
    -0.69
    ossip
    -0.67
    CT
    -0.67
    cci
    -0.67
    POSITIVE LOGITS
    lord
    1.17
     lord
    1.08
    lords
    0.91
    ribut
    0.79
    uyomi
    0.78
     lords
    0.76
    doms
    0.72
     Vlad
    0.70
    terday
    0.69
    veland
    0.69
    Activations Density 0.024%

    No Known Activations