© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 16840
    Prev
    Next
    INDEX
    Explanations

    themes of controversy and criticism related to authority, particularly in the context of governance and societal issues

    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
    1:0.03
    2:0.04
    3:0.05
    4:0.23
    5:0.05
    6:0.03
    7:0.09
    8:0.02
    9:0.16
    10:0.04
    11:0.18
    Negative Logits
    eva
    -2.47
    aughtered
    -2.46
    eday
    -2.24
    �
    -2.12
    ulhu
    -2.05
    brates
    -2.00
    ..."
    -1.98
    !!!!
    -1.96
    psc
    -1.93
    brate
    -1.92
    POSITIVE LOGITS
     reluctance
    3.93
     unwillingness
    3.65
     familiarity
    3.60
     reliance
    3.48
     inexper
    3.44
     scarcity
    3.24
     animosity
    3.21
     hostility
    3.21
     deficiencies
    3.18
     lack
    3.16
    Activations Density 0.468%

    No Known Activations