© 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. 20746
    Prev
    Next
    INDEX
    Explanations

    significant social and political issues affecting communities and individuals

    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
    0:0.03
    1:0.02
    2:0.02
    3:0.13
    4:0.03
    5:0.08
    6:0.38
    7:0.04
    8:0.02
    9:0.02
    10:0.09
    11:0.09
    Negative Logits
    inventoryQuantity
    -3.42
    Ru
    -3.16
     Tucker
    -3.13
     Burke
    -3.12
     Sponge
    -3.12
     Sullivan
    -3.09
     Schmidt
    -3.08
    izons
    -2.96
     Neptune
    -2.92
     Appalachian
    -2.92
    POSITIVE LOGITS
    ollah
    3.09
     CM
    3.03
     Rams
    3.00
    �
    2.94
    idav
    2.92
    CM
    2.63
     gland
    2.59
    volt
    2.57
     pent
    2.56
    umer
    2.56
    Activations Density 0.331%

    No Known Activations