© 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 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. 13046
    Prev
    Next
    INDEX
    Explanations

    references to geographical and social contexts, particularly related to Bolivia's agricultural practices and challenges

    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
    0:0.07
    1:0.02
    2:0.04
    3:0.03
    4:0.06
    5:0.03
    6:0.24
    7:0.05
    8:0.11
    9:0.22
    10:0.02
    11:0.04
    Negative Logits
    Tile
    -4.52
     Kenyan
    -4.01
    Mega
    -3.82
    ellen
    -3.73
     McK
    -3.69
    Meg
    -3.67
     Mega
    -3.59
    ِ
    -3.57
    yers
    -3.52
    oultry
    -3.47
    POSITIVE LOGITS
     Bol
    11.23
    bol
    7.31
     bol
    7.14
     Bolivia
    6.73
     Tol
    4.81
     Korra
    4.67
     Bolt
    4.54
    Bal
    4.29
     Kol
    4.24
     Venezuel
    4.18
    Activations Density 0.002%

    No Known Activations