© 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. 2343
    Prev
    Next
    INDEX
    Explanations

    diminutive or diminutive-like names and terms

    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
    1:0.01
    2:0.03
    3:0.08
    4:0.02
    5:0.05
    6:0.18
    7:0.02
    8:0.03
    9:0.43
    10:0.02
    11:0.03
    Negative Logits
     Sora
    -4.24
    oral
    -3.50
     Ark
    -3.33
     Clone
    -3.32
    Cor
    -3.31
     Coral
    -3.29
    Ark
    -3.26
    ora
    -3.26
     Xue
    -3.22
     Cor
    -3.22
    POSITIVE LOGITS
    mann
    6.95
     Mann
    5.32
    heimer
    4.27
    ahn
    4.26
     Muller
    4.25
    uld
    4.00
    heim
    3.96
    dm
    3.96
     Berg
    3.88
    mitt
    3.85
    Activations Density 0.003%

    No Known Activations