© 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. 3283
    Prev
    Next
    INDEX
    Explanations

    references to legal or regulatory actions in texts

    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
    0:0.08
    1:0.02
    2:0.06
    3:0.03
    4:0.08
    5:0.03
    6:0.26
    7:0.04
    8:0.09
    9:0.19
    10:0.01
    11:0.06
    Negative Logits
     voy
    -3.46
    vine
    -3.29
    ────
    -3.20
     fortun
    -3.08
    ulhu
    -3.08
     civilization
    -3.06
     corros
    -3.06
     sauce
    -3.03
     beetle
    -3.02
    acid
    -3.01
    POSITIVE LOGITS
     PB
    6.14
     RM
    6.08
     RG
    5.81
     KB
    5.71
     FN
    5.65
     BM
    5.56
     HC
    5.42
     JM
    5.41
     SB
    5.39
     BF
    5.37
    Activations Density 0.131%

    No Known Activations