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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14927
    Prev
    Next
    INDEX
    Explanations

    references to specific products and their features

    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
    0:0.24
    1:0.08
    2:0.09
    3:0.06
    4:0.05
    5:0.02
    6:0.05
    7:0.14
    8:0.02
    9:0.04
    10:0.11
    11:0.05
    Negative Logits
     corrid
    -3.76
     Romero
    -3.69
     Chavez
    -3.60
     Kass
    -3.55
     Herrera
    -3.19
     Giov
    -3.16
     Sonny
    -3.15
     Christina
    -3.10
     Freddy
    -3.05
     Akira
    -3.02
    POSITIVE LOGITS
     Surface
    7.20
     tablet
    4.86
     MacBook
    4.71
     tablets
    4.46
     Tablet
    4.35
     iPad
    4.23
     laptop
    4.11
     Lenovo
    4.11
     Microsoft
    4.04
    Microsoft
    4.01
    Activations Density 0.011%

    No Known Activations