© 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. 20557
    Prev
    Next
    INDEX
    Explanations

    instances of action and identity in narratives involving people

    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
    0:0.10
    1:0.03
    2:0.06
    3:0.04
    4:0.04
    5:0.04
    6:0.24
    7:0.05
    8:0.09
    9:0.18
    10:0.03
    11:0.04
    Negative Logits
     Runner
    -3.91
     Luthor
    -3.56
     newsp
    -3.35
     cape
    -3.31
     Tacoma
    -3.27
     Torch
    -3.26
     torches
    -3.26
     Euros
    -3.25
     XCOM
    -3.23
     asteroid
    -3.22
    POSITIVE LOGITS
    Mah
    10.15
     Mah
    9.72
     mah
    6.58
     Moh
    5.46
    Moh
    4.72
     Bod
    4.05
    bh
    3.90
     Nich
    3.83
     Mississ
    3.71
     Hay
    3.69
    Activations Density 0.005%

    No Known Activations