© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 3786
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the significance or importance of concepts or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.05
    3:0.04
    4:0.11
    5:0.02
    6:0.24
    7:0.24
    8:0.03
    9:0.03
    10:0.06
    11:0.07
    Negative Logits
    quartered
    -1.68
    overed
    -1.53
    joining
    -1.48
    elist
    -1.43
     spiders
    -1.42
    ottage
    -1.37
    ENTS
    -1.34
    arthed
    -1.33
    igers
    -1.33
    owe
    -1.32
    POSITIVE LOGITS
    lot
    1.58
     Playoff
    1.39
    auntlet
    1.33
     fortun
    1.30
     differently
    1.28
     luck
    1.28
     Clancy
    1.27
     CSI
    1.27
     rou
    1.26
    pause
    1.25
    Activations Density 0.019%

    No Known Activations