© 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. 16478
    Prev
    Next
    INDEX
    Explanations

    instances of evidence or reports related to human rights violations

    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
    0:0.06
    1:0.02
    2:0.10
    3:0.04
    4:0.08
    5:0.07
    6:0.18
    7:0.05
    8:0.08
    9:0.24
    10:0.02
    11:0.03
    Negative Logits
    ctrl
    -3.65
     Schr
    -3.63
     Schl
    -3.48
    Thompson
    -3.47
     Nich
    -3.38
     roller
    -3.18
     Thompson
    -3.17
    nerg
    -3.16
     Franch
    -3.06
     Rollins
    -3.03
    POSITIVE LOGITS
     Amnesty
    8.80
    nesty
    6.51
     amnesty
    5.20
    Am
    4.25
     Umb
    4.11
    Amb
    3.91
    オ
    3.91
     UAE
    3.87
     Asylum
    3.82
    EVA
    3.77
    Activations Density 0.003%

    No Known Activations