© 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. 21174
    Prev
    Next
    INDEX
    Explanations

    mentions of sensitive information and data regarding individuals, particularly in the context of immigration and personal records

    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
    0:0.12
    1:0.03
    2:0.10
    3:0.13
    4:0.04
    5:0.33
    6:0.03
    7:0.05
    8:0.04
    9:0.03
    10:0.04
    11:0.02
    Negative Logits
     workaround
    -2.75
     resize
    -2.52
     limbo
    -2.52
     sandbox
    -2.39
     scanner
    -2.32
    Solution
    -2.29
     solution
    -2.29
     scaven
    -2.17
     dilemma
    -2.13
    rescent
    -2.10
    POSITIVE LOGITS
     Influ
    2.48
     Birth
    2.47
     births
    2.46
     Celebrity
    2.39
     personalities
    2.36
     Years
    2.31
     Occupations
    2.28
     Events
    2.27
     Rebell
    2.16
     Races
    2.15
    Activations Density 0.395%

    No Known Activations