© 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. 18829
    Prev
    Next
    INDEX
    Explanations

    phrases related to business transactions and negotiations

    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
    0:0.07
    1:0.03
    2:0.08
    3:0.04
    4:0.05
    5:0.05
    6:0.34
    7:0.03
    8:0.05
    9:0.16
    10:0.03
    11:0.02
    Negative Logits
     Murray
    -4.09
    Scot
    -3.93
     Pam
    -3.90
    Murray
    -3.81
     skiing
    -3.77
     Sho
    -3.73
    �
    -3.67
     Roose
    -3.65
     Runes
    -3.61
     Guth
    -3.52
    POSITIVE LOGITS
     Cell
    9.75
     cell
    9.53
    Cell
    9.47
    cell
    8.62
     Cells
    8.61
     cells
    8.53
    cells
    7.83
     cellular
    6.72
     Cellular
    6.27
    ocyte
    4.97
    Activations Density 0.019%

    No Known Activations