© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 15014
    Prev
    Next
    INDEX
    Explanations

    phrases related to evolution and the arguments surrounding it

    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
    0:0.22
    1:0.06
    2:0.04
    3:0.11
    4:0.11
    5:0.02
    6:0.06
    7:0.15
    8:0.02
    9:0.04
    10:0.05
    11:0.08
    Negative Logits
     Havana
    -3.19
     opium
    -3.08
     heroin
    -3.01
     fentanyl
    -2.99
    proc
    -2.92
     morphine
    -2.90
     Elastic
    -2.90
     BlackBerry
    -2.81
     cocaine
    -2.81
     narcotics
    -2.76
    POSITIVE LOGITS
     Creation
    4.72
     Dawkins
    3.96
     creation
    3.76
    Cre
    3.75
     atheism
    3.70
    creation
    3.67
     embry
    3.63
     biblical
    3.44
     dinosaurs
    3.42
     Biblical
    3.42
    Activations Density 0.029%

    No Known Activations