© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 19350
    Prev
    Next
    INDEX
    Explanations

    mentions of Edward Snowden and discussions around whistleblowing and asylum

    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
    0:0.05
    1:0.03
    2:0.13
    3:0.04
    4:0.06
    5:0.03
    6:0.17
    7:0.09
    8:0.04
    9:0.23
    10:0.03
    11:0.05
    Negative Logits
    carb
    -3.50
    %%%%
    -3.37
    Kal
    -3.08
     pelvic
    -3.07
     bourbon
    -3.00
    agin
    -2.97
    gans
    -2.95
     bones
    -2.94
     bone
    -2.90
    becue
    -2.86
    POSITIVE LOGITS
     Snowden
    9.44
    Snow
    7.89
     Greenwald
    5.88
     Edward
    5.49
    Edward
    5.32
     whistlebl
    5.21
     NSA
    5.18
     whistleblower
    5.18
    NSA
    5.15
     Assange
    4.87
    Activations Density 0.016%

    No Known Activations