© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 21444
    Prev
    Next
    INDEX
    Explanations

    interactions involving conflict or tension between characters

    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
    0:0.06
    1:0.03
    2:0.10
    3:0.17
    4:0.08
    5:0.09
    6:0.03
    7:0.11
    8:0.09
    9:0.03
    10:0.08
    11:0.06
    Negative Logits
    itutional
    -2.42
    �
    -2.37
    emporary
    -2.23
     quarterly
    -2.19
    iberal
    -2.17
    Regular
    -2.17
     internationally
    -2.12
    soType
    -2.09
     norms
    -2.09
    national
    -2.09
    POSITIVE LOGITS
     Luffy
    3.40
     Vegeta
    2.69
     Gohan
    2.65
     escapes
    2.58
     ambush
    2.54
     flashback
    2.51
     Wally
    2.48
     retrie
    2.46
     Frieza
    2.42
     Sawyer
    2.40
    Activations Density 0.468%

    No Known Activations