© 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. 358
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a significant threat or concern to livelihoods and communities

    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
    0:0.07
    1:0.04
    2:0.05
    3:0.03
    4:0.06
    5:0.02
    6:0.22
    7:0.06
    8:0.08
    9:0.25
    10:0.02
    11:0.05
    Negative Logits
     Asgard
    -4.63
    ongs
    -4.29
     Loki
    -4.14
     Odin
    -4.05
    heng
    -3.89
     ENG
    -3.83
    ong
    -3.57
    ModLoader
    -3.52
    ignt
    -3.39
     lantern
    -3.38
    POSITIVE LOGITS
     Casey
    9.93
    Case
    6.02
     Cory
    4.61
     Chuck
    4.27
     Lowry
    4.19
     Coulter
    4.14
     Boyle
    4.13
     Leah
    4.07
     Leslie
    4.02
     Danielle
    4.02
    Activations Density 0.002%

    No Known Activations