© 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. 3-RES-JB
    11. 3923
    Prev
    Next
    INDEX
    Explanations

    words related to roles or positions of authority and control, such as moderators, admins, and curators

    oai_token-act-pair · gpt-3.5-turbo

    references to moderators and moderation in discussions or content

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Winds
    -0.75
    åĮ
    -0.75
    usions
    -0.73
    ties
    -0.73
    TA
    -0.72
    reads
    -0.69
    bra
    -0.67
    urst
    -0.67
    JC
    -0.66
    psc
    -0.66
    POSITIVE LOGITS
     moderators
    1.28
     moderator
    1.01
     moderation
    0.94
     moder
    0.91
     AMA
    0.80
     Moder
    0.72
    iquette
    0.72
     admins
    0.70
     redd
    0.69
     Mods
    0.69
    Activations Density 0.018%

    No Known Activations