© 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. 14826
    Prev
    Next
    INDEX
    Explanations

    quotes and statements regarding public or governmental issues

    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
    0:0.13
    1:0.06
    2:0.13
    3:0.06
    4:0.05
    5:0.03
    6:0.09
    7:0.07
    8:0.02
    9:0.04
    10:0.22
    11:0.06
    Negative Logits
     Ukrain
    -3.32
    icio
    -3.28
    cott
    -3.03
    Sov
    -2.97
     Swamp
    -2.94
     Rhino
    -2.82
    antes
    -2.74
    orest
    -2.73
     Cah
    -2.70
     Havana
    -2.70
    POSITIVE LOGITS
     MB
    9.96
    MB
    7.09
     KB
    5.80
     GB
    5.11
    KB
    4.87
     MBA
    4.79
    mb
    4.51
     PB
    4.44
     TB
    4.39
    PB
    4.34
    Activations Density 0.002%

    No Known Activations