© 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. 24230
    Prev
    Next
    INDEX
    Explanations

    references to development and progress within various contexts

    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
    0:0.06
    1:0.04
    2:0.07
    3:0.08
    4:0.04
    5:0.05
    6:0.14
    7:0.03
    8:0.04
    9:0.32
    10:0.04
    11:0.03
    Negative Logits
    ucket
    -3.54
     sle
    -3.51
     Wool
    -3.30
     Huck
    -3.29
     MU
    -3.22
    lees
    -3.14
     HI
    -3.14
     ultras
    -3.12
     wal
    -3.10
     Sle
    -3.07
    POSITIVE LOGITS
     Development
    5.60
    development
    5.54
    Development
    5.05
    Develop
    4.98
     development
    4.79
    develop
    4.75
     Develop
    4.68
     developmental
    4.58
    developed
    4.16
     Dev
    4.16
    Activations Density 0.003%

    No Known Activations