© 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. 19825
    Prev
    Next
    INDEX
    Explanations

    references to environmental conditions and hazards

    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
    1:0.01
    2:0.06
    3:0.28
    4:0.02
    5:0.08
    6:0.01
    7:0.07
    8:0.03
    9:0.01
    10:0.32
    11:0.02
    Negative Logits
     plateau
    -1.91
     Completed
    -1.88
     Complete
    -1.87
     graduating
    -1.85
     tidy
    -1.84
     FANTASY
    -1.83
     Cust
    -1.75
     abstinence
    -1.75
    achelor
    -1.74
     comfortable
    -1.73
    POSITIVE LOGITS
    attacks
    3.11
     hazards
    3.06
     attacks
    2.99
     onslaught
    2.90
     threats
    2.84
     assaults
    2.72
     intrusion
    2.67
     risks
    2.64
     dangers
    2.63
     viruses
    2.62
    Activations Density 0.245%

    No Known Activations