© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 11644
    Prev
    Next
    INDEX
    Explanations

    references to criminal activity and legal terminology

    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
    0:0.04
    1:0.04
    2:0.11
    3:0.07
    4:0.04
    5:0.05
    6:0.27
    7:0.04
    8:0.04
    9:0.19
    10:0.03
    11:0.03
    Negative Logits
     pipeline
    -3.66
     Asus
    -3.56
     Farn
    -3.54
     GW
    -3.34
     Tillerson
    -3.31
     OG
    -3.29
     Huang
    -3.28
     Kass
    -3.26
    template
    -3.25
     Flores
    -3.21
    POSITIVE LOGITS
     Crime
    8.36
     crime
    8.35
    crime
    8.09
    Crime
    8.03
     criminals
    6.87
     Crim
    6.76
     crimes
    6.71
     criminality
    6.54
     crim
    6.27
     criminal
    6.25
    Activations Density 0.028%

    No Known Activations