© 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. 14797
    Prev
    Next
    INDEX
    Explanations

    references to park management and development activities

    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
    0:0.12
    1:0.03
    2:0.04
    3:0.03
    4:0.05
    5:0.02
    6:0.09
    7:0.37
    8:0.02
    9:0.03
    10:0.05
    11:0.10
    Negative Logits
     coc
    -2.29
    anson
    -2.13
    Boot
    -2.10
     lipstick
    -2.08
    VPN
    -2.04
     Filip
    -2.03
     ans
    -1.96
     Moons
    -1.93
    boot
    -1.93
     Mold
    -1.92
    POSITIVE LOGITS
    erie
    2.06
    �
    2.01
    ocene
    1.97
     1932
    1.95
    irty
    1.94
    erb
    1.93
    ファ
    1.91
     Dra
    1.90
    ERAL
    1.88
     Roosevelt
    1.87
    Activations Density 0.033%

    No Known Activations