© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 20596
    Prev
    Next
    INDEX
    Explanations

    concerns related to environmental issues and conservation efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.19
    1:0.05
    2:0.06
    3:0.05
    4:0.05
    5:0.02
    6:0.06
    7:0.19
    8:0.02
    9:0.05
    10:0.13
    11:0.08
    Negative Logits
     Romo
    -3.06
     Garfield
    -2.87
     Glock
    -2.65
     Teddy
    -2.58
     Guns
    -2.55
    raints
    -2.52
     pistols
    -2.47
     revolver
    -2.42
     Cody
    -2.42
     Violence
    -2.39
    POSITIVE LOGITS
     algae
    6.10
     reefs
    3.58
     coral
    3.58
     seaw
    3.44
     chlor
    3.33
     reef
    3.27
     nutrient
    3.19
    gae
    3.15
     Coral
    3.15
     shrimp
    3.08
    Activations Density 0.004%

    No Known Activations