© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 21099
    Prev
    Next
    INDEX
    Explanations

    references to controversial statements and political commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    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
    2:0.03
    3:0.04
    4:0.08
    5:0.19
    6:0.03
    7:0.03
    8:0.02
    9:0.42
    10:0.02
    11:0.04
    Negative Logits
     completes
    -2.37
    Phase
    -2.36
     feasibility
    -2.33
    capacity
    -2.29
     manageable
    -2.17
     recovers
    -2.16
     completion
    -2.15
     manpower
    -2.10
     perfected
    -2.06
     assemb
    -2.04
    POSITIVE LOGITS
     criticizing
    3.32
     praising
    3.07
     condemning
    3.04
     accusing
    3.02
     denouncing
    2.97
    か
    2.95
     implying
    2.94
     derogatory
    2.92
     mocking
    2.91
     insulting
    2.88
    Activations Density 0.330%

    No Known Activations