© 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. 13915
    Prev
    Next
    INDEX
    Explanations

    Java version details and settings

    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
    0:0.11
    1:0.03
    2:0.05
    3:0.09
    4:0.05
    5:0.07
    6:0.06
    7:0.04
    8:0.31
    9:0.06
    10:0.04
    11:0.05
    Negative Logits
     Ukrainians
    -4.33
     Halifax
    -4.29
     Ukrainian
    -4.12
     Ottawa
    -3.93
     Ukraine
    -3.80
    Ott
    -3.78
     Sabres
    -3.72
     Capitals
    -3.69
    Ukraine
    -3.61
    �
    -3.60
    POSITIVE LOGITS
     java
    6.74
     Java
    6.30
    java
    5.86
    Java
    5.61
     JD
    4.85
     android
    4.76
     jar
    4.43
    JD
    4.35
    android
    4.30
     Pasadena
    4.26
    Activations Density 0.044%

    No Known Activations