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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 1159
    Prev
    Next
    INDEX
    Explanations

    connections and relationships between numerical values and their context

    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
    0:0.04
    1:0.06
    2:0.06
    3:0.07
    4:0.05
    5:0.04
    6:0.05
    7:0.45
    8:0.03
    9:0.04
    10:0.04
    11:0.02
    Negative Logits
     nailed
    -2.77
    estamp
    -2.49
     Stout
    -2.30
    wed
    -2.30
    Sharp
    -2.30
     Trident
    -2.26
     sober
    -2.24
    wark
    -2.23
     drilled
    -2.20
    pain
    -2.19
    POSITIVE LOGITS
     secondary
    4.17
     periphery
    3.49
    secondary
    3.33
    illary
    3.32
     Secondary
    3.25
     secondly
    3.11
     peripheral
    3.06
     Secondly
    3.00
    Secondly
    3.00
    cellaneous
    2.99
    Activations Density 0.086%

    No Known Activations