© 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. 9-ATT-KK
    11. 10787
    Prev
    Next
    INDEX
    Explanations

    sentences indicating official announcements or statements

    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
    0:0.08
    1:0.03
    2:0.04
    3:0.04
    4:0.06
    5:0.03
    6:0.18
    7:0.04
    8:0.09
    9:0.28
    10:0.02
    11:0.03
    Negative Logits
     Roz
    -4.11
     cryptoc
    -4.04
    Pol
    -3.99
     Warsaw
    -3.71
    ł
    -3.69
    catentry
    -3.62
    ulz
    -3.60
     Poland
    -3.56
     [&
    -3.51
     Activision
    -3.45
    POSITIVE LOGITS
     Henderson
    10.56
     Hend
    7.67
    hend
    5.60
     Hendricks
    5.13
     Edgar
    4.71
     Petersen
    4.67
     Hem
    4.39
     Kend
    4.12
     Hume
    4.06
    horn
    4.01
    Activations Density 0.002%

    No Known Activations