© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 27286
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate moderation or management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.04
    3:0.06
    4:0.13
    5:0.02
    6:0.03
    7:0.38
    8:0.03
    9:0.03
    10:0.13
    11:0.06
    Negative Logits
    覚醒
    -1.68
     fulfilled
    -1.68
    paralle
    -1.55
    Catalog
    -1.53
     envision
    -1.51
     fulfillment
    -1.49
    retched
    -1.45
    rists
    -1.44
    士
    -1.43
    INFO
    -1.42
    POSITIVE LOGITS
     moder
    2.02
     moderation
    1.74
     Dialogue
    1.65
     Atmosp
    1.58
     commenting
    1.51
     dialogue
    1.49
     democratically
    1.46
     debates
    1.45
     dissenting
    1.45
     debate
    1.44
    Activations Density 0.001%

    No Known Activations