© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 421
    Prev
    Next
    INDEX
    Explanations

    instances of technical instructions or specifications

    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
    0:0.15
    1:0.03
    2:0.07
    3:0.06
    4:0.03
    5:0.06
    6:0.04
    7:0.05
    8:0.35
    9:0.04
    10:0.03
    11:0.04
    Negative Logits
     Galaxy
    -3.70
     Garc
    -3.69
     MLS
    -3.42
     Keane
    -3.42
     Bundesliga
    -3.35
    �
    -3.30
     Confederate
    -3.24
     Alonso
    -3.24
     Sao
    -3.22
     Liga
    -3.17
    POSITIVE LOGITS
     bash
    4.45
    bash
    4.20
     Bash
    3.58
     Zoro
    3.42
    awk
    3.39
    ariat
    3.07
     Hare
    3.05
    chery
    2.96
    Shell
    2.79
    #$
    2.77
    Activations Density 0.000%

    No Known Activations