© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 21095
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to chemical processes and interactions

    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
    0:0.09
    1:0.03
    2:0.09
    3:0.05
    4:0.05
    5:0.05
    6:0.18
    7:0.05
    8:0.10
    9:0.18
    10:0.02
    11:0.06
    Negative Logits
    wen
    -4.69
     Benn
    -3.77
    Beast
    -3.74
     Woo
    -3.67
    UX
    -3.65
     cowork
    -3.64
     Beast
    -3.48
     Bomber
    -3.46
     Koen
    -3.39
     Frie
    -3.38
    POSITIVE LOGITS
     sodium
    8.60
     Sodium
    8.01
     salt
    6.54
     salts
    6.37
     potassium
    6.21
     salty
    6.15
    Salt
    6.10
    assium
    5.96
    odium
    5.94
     Na
    5.21
    Activations Density 0.004%

    No Known Activations