© 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. 9-ATT-KK
    11. 22433
    Prev
    Next
    INDEX
    Explanations

    evidence related to fossil discovery and evaluation in the context of evolution

    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
    0:0.22
    1:0.03
    2:0.17
    3:0.07
    4:0.05
    5:0.09
    6:0.07
    7:0.04
    8:0.06
    9:0.08
    10:0.04
    11:0.03
    Negative Logits
    dule
    -2.69
     sched
    -2.61
     PID
    -2.56
     Administ
    -2.53
     Mbps
    -2.51
     wards
    -2.51
     WhatsApp
    -2.47
     rollout
    -2.46
     scheduling
    -2.45
    ORPG
    -2.45
    POSITIVE LOGITS
     fossils
    6.12
     fossil
    5.66
     Foss
    5.01
     dinosaurs
    4.19
     Dinosaur
    4.06
     dinosaur
    3.97
     geological
    3.93
    inosaur
    3.93
     shark
    3.87
    osaurus
    3.72
    Activations Density 0.003%

    No Known Activations