© 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. 11637
    Prev
    Next
    INDEX
    Explanations

    references to safety and precautionary measures

    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
    1:0.03
    2:0.04
    3:0.04
    4:0.03
    5:0.05
    6:0.30
    7:0.03
    8:0.07
    9:0.19
    10:0.03
    11:0.06
    Negative Logits
    Toy
    -4.44
     McGregor
    -3.84
     McN
    -3.71
     Reggie
    -3.68
    TPP
    -3.55
     Nieto
    -3.54
     Kraft
    -3.46
     Vaughan
    -3.43
     Tyson
    -3.41
     Vietnamese
    -3.39
    POSITIVE LOGITS
     Bas
    9.14
    Bas
    9.02
    bas
    7.38
     bas
    6.48
     BAS
    5.65
     basin
    5.21
     basement
    5.05
     Das
    4.58
     Bil
    4.46
     Basin
    4.42
    Activations Density 0.002%

    No Known Activations