© 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. 20889
    Prev
    Next
    INDEX
    Explanations

    references to technical specifications and system functionality

    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
    0:0.08
    1:0.29
    2:0.07
    3:0.06
    4:0.06
    5:0.02
    6:0.06
    7:0.10
    8:0.03
    9:0.03
    10:0.07
    11:0.07
    Negative Logits
     Khe
    -3.20
     Lazarus
    -3.02
     Haley
    -2.75
     Stam
    -2.56
    ynthesis
    -2.55
    UCT
    -2.48
     Pets
    -2.46
    Brew
    -2.45
     Hath
    -2.45
    externalActionCode
    -2.43
    POSITIVE LOGITS
     edge
    6.71
     Edge
    6.70
    Edge
    6.02
     edges
    5.96
    edge
    5.34
     periphery
    3.70
     edged
    3.65
     corners
    3.57
     perimeter
    3.53
     corner
    3.50
    Activations Density 0.009%

    No Known Activations