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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 7914
    Prev
    Next
    INDEX
    Explanations

    key phrases related to specific events or elements in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.16
    1:0.07
    2:0.06
    3:0.08
    4:0.06
    5:0.03
    6:0.12
    7:0.12
    8:0.02
    9:0.03
    10:0.09
    11:0.08
    Negative Logits
     Cohen
    -2.84
     MSM
    -2.77
    phis
    -2.73
     Weber
    -2.59
     Memphis
    -2.59
     Ferguson
    -2.55
     UCLA
    -2.54
     Compton
    -2.52
    headers
    -2.52
    Mos
    -2.51
    POSITIVE LOGITS
    Adventure
    6.88
     Adventure
    6.67
     adventure
    5.70
     Adventures
    5.30
     adventures
    4.95
     adventurers
    4.77
     adventurer
    4.66
    venture
    4.00
     Dungeon
    3.67
     Pathfinder
    3.64
    Activations Density 0.005%

    No Known Activations