© 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. 466
    Prev
    Next
    INDEX
    Explanations

    references to classified information or security breaches

    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
    0:0.20
    1:0.02
    2:0.19
    3:0.11
    4:0.03
    5:0.11
    6:0.02
    7:0.06
    8:0.11
    9:0.03
    10:0.04
    11:0.03
    Negative Logits
    nesday
    -2.78
    ogie
    -2.65
    iatus
    -2.55
    ourney
    -2.54
     Paleo
    -2.53
     Rally
    -2.51
     Comedy
    -2.50
     Ven
    -2.43
     Taste
    -2.40
    Beer
    -2.39
    POSITIVE LOGITS
     declass
    5.32
     classified
    4.47
    classified
    4.22
     classification
    3.97
     encryption
    3.50
     Classification
    3.26
    CLASSIFIED
    3.15
     classify
    3.06
     espionage
    2.98
     redacted
    2.96
    Activations Density 0.014%

    No Known Activations