© 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. 9917
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and character interactions in storytelling contexts

    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
    2:0.07
    3:0.05
    4:0.02
    5:0.04
    6:0.25
    7:0.04
    8:0.04
    9:0.28
    10:0.03
    11:0.02
    Negative Logits
    ヴァ
    -3.87
    ズ
    -3.67
    zn
    -3.62
    ーク
    -3.44
    aspers
    -3.42
    Ve
    -3.41
    vir
    -3.38
    vironment
    -3.35
    vol
    -3.27
     Nept
    -3.27
    POSITIVE LOGITS
     Hang
    8.86
     hang
    8.37
    hang
    7.27
     hangs
    6.46
     hung
    6.41
     hanging
    6.34
     hanged
    6.14
     Hamm
    5.05
     Lang
    4.47
    angs
    4.41
    Activations Density 0.002%

    No Known Activations