© 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. 11690
    Prev
    Next
    INDEX
    Explanations

    terms associated with incidents of violence or crime

    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
    2:0.04
    3:0.06
    4:0.03
    5:0.04
    6:0.08
    7:0.03
    8:0.05
    9:0.48
    10:0.03
    11:0.03
    Negative Logits
    Draft
    -3.85
    draft
    -3.72
     Shir
    -3.58
    iri
    -3.39
    MAG
    -3.18
    ARP
    -3.11
     Boh
    -3.10
     Piper
    -3.06
     Chop
    -3.06
     Lift
    -3.06
    POSITIVE LOGITS
    es
    5.17
    nes
    5.13
     Mes
    4.77
    Tes
    4.74
     es
    4.74
    ES
    4.66
     mes
    4.50
    tes
    4.30
    és
    4.26
     Tes
    4.26
    Activations Density 0.025%

    No Known Activations