© 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. 9-ATT-KK
    11. 2145
    Prev
    Next
    INDEX
    Explanations

    references to control and power dynamics within societal structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.02
    2:0.18
    3:0.16
    4:0.02
    5:0.04
    6:0.01
    7:0.04
    8:0.03
    9:0.02
    10:0.33
    11:0.01
    Negative Logits
    existent
    -2.19
    liv
    -2.18
     seriousness
    -2.16
     enough
    -2.09
     sufficiently
    -1.96
    hib
    -1.94
     Enough
    -1.93
    enough
    -1.91
    compliance
    -1.88
     screenings
    -1.86
    POSITIVE LOGITS
     derives
    3.71
     sprang
    3.21
     derive
    3.21
     originated
    2.72
     descended
    2.67
     derived
    2.66
     rests
    2.65
     emerges
    2.60
     assumes
    2.56
     deriv
    2.56
    Activations Density 0.017%

    No Known Activations