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

    Neuronpedia

    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. 660
    Prev
    Next
    INDEX
    Explanations

    interactions or exchanges between characters in a narrative 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
    0:0.05
    1:0.05
    2:0.09
    3:0.14
    4:0.19
    5:0.08
    6:0.03
    7:0.13
    8:0.04
    9:0.02
    10:0.08
    11:0.04
    Negative Logits
     advocated
    -2.47
    redit
    -2.40
    VP
    -2.31
    oided
    -2.30
    NJ
    -2.23
     benefited
    -2.23
    Source
    -2.21
    actionDate
    -2.20
    valued
    -2.19
    itutional
    -2.16
    POSITIVE LOGITS
     stares
    3.91
     wakes
    3.71
     pauses
    3.70
     glances
    3.65
     leans
    3.52
     yells
    3.51
     emerges
    3.47
     shakes
    3.46
     hangs
    3.42
     flashes
    3.40
    Activations Density 0.514%

    No Known Activations