© 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. 5187
    Prev
    Next
    INDEX
    Explanations

    numeric data such as counts or values associated with user activity and posts

    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
    1:0.07
    2:0.04
    3:0.17
    4:0.05
    5:0.08
    6:0.11
    7:0.05
    8:0.02
    9:0.21
    10:0.06
    11:0.03
    Negative Logits
     salads
    -3.44
     Cater
    -3.35
     Shuttle
    -3.29
     Honey
    -3.17
     Schultz
    -3.13
     Meier
    -3.01
     Bradley
    -3.00
     Hoffman
    -2.61
     Hoff
    -2.61
     SEM
    -2.55
    POSITIVE LOGITS
    ブ
    2.51
    uxe
    2.49
    enes
    2.48
    ノ
    2.44
    �
    2.42
    daq
    2.41
    ibur
    2.35
    DAQ
    2.33
    lb
    2.31
    ーテ
    2.27
    Activations Density 0.001%

    No Known Activations