© 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. 20010
    Prev
    Next
    INDEX
    Explanations

    references to political and social belief systems

    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
    2:0.04
    3:0.05
    4:0.06
    5:0.53
    6:0.02
    7:0.04
    8:0.04
    9:0.08
    10:0.02
    11:0.04
    Negative Logits
    ntil
    -3.08
    rather
    -2.78
    apter
    -2.78
     hindsight
    -2.73
    istor
    -2.64
    raq
    -2.63
    emate
    -2.56
    ascript
    -2.52
    failed
    -2.50
    until
    -2.45
    POSITIVE LOGITS
     also
    7.15
    also
    6.56
     ALSO
    5.65
     too
    5.35
     likewise
    5.32
     additionally
    4.93
    Additionally
    4.89
    Also
    4.85
     furthermore
    4.57
     Also
    4.53
    Activations Density 0.689%

    No Known Activations