© 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. 9-ATT-KK
    11. 4103
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to measurements, statistics, and comparisons in performance

    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
    0:0.04
    1:0.02
    2:0.04
    3:0.04
    4:0.05
    5:0.04
    6:0.16
    7:0.03
    8:0.02
    9:0.46
    10:0.02
    11:0.03
    Negative Logits
     Palmer
    -3.67
     Nightmares
    -3.45
     Sabb
    -3.28
    ister
    -3.27
     Nightmare
    -3.15
    arah
    -3.04
    �
    -3.04
    amara
    -3.02
    ara
    -3.00
     extingu
    -2.96
    POSITIVE LOGITS
    Gs
    6.01
    G
    5.99
     DG
    5.44
    GD
    5.32
     g
    5.25
     Gaz
    5.25
     G
    5.18
    GG
    5.17
     GG
    5.17
    gat
    5.12
    Activations Density 0.282%

    No Known Activations