© 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. 16727
    Prev
    Next
    INDEX
    Explanations

    phrases related to political discourse and direct actions against perceived injustices

    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
    0:0.04
    1:0.43
    2:0.06
    3:0.04
    4:0.06
    5:0.04
    6:0.04
    7:0.09
    8:0.03
    9:0.04
    10:0.04
    11:0.05
    Negative Logits
     Reloaded
    -2.61
     subdued
    -2.59
    leted
    -2.40
     inactive
    -2.38
     distant
    -2.37
     dormant
    -2.31
    uni
    -2.29
     Drawn
    -2.26
     Lur
    -2.26
     softened
    -2.20
    POSITIVE LOGITS
     Right
    7.28
    Right
    7.20
     right
    7.00
    right
    6.70
     RIGHT
    6.68
    Left
    4.99
     left
    4.70
    left
    4.69
     Left
    4.62
     Wrong
    4.46
    Activations Density 0.145%

    No Known Activations