© 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. 14950
    Prev
    Next
    INDEX
    Explanations

    instances of numerical expressions and quantifiable data

    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
    0:0.03
    1:0.04
    2:0.03
    3:0.07
    4:0.11
    5:0.15
    6:0.01
    7:0.04
    8:0.15
    9:0.01
    10:0.02
    11:0.28
    Negative Logits
    !'
    -3.97
    )'
    -3.79
    ':
    -3.54
    ,'
    -3.43
    ?'
    -3.33
    .'
    -3.26
    :'
    -3.22
    ,'"
    -2.99
    .�
    -2.93
    Ohio
    -2.92
    POSITIVE LOGITS
     "
    3.10
     Tasman
    2.85
     "(
    2.75
     ".
    2.70
     Queensland
    2.58
     "'
    2.58
    "/>
    2.50
    "
    2.45
     "[
    2.44
     Pearce
    2.38
    Activations Density 0.042%

    No Known Activations