© 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. 3698
    Prev
    Next
    INDEX
    Explanations

    specific technical or scientific terminology related to protocols or systems

    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
    2:0.06
    3:0.04
    4:0.05
    5:0.04
    6:0.28
    7:0.04
    8:0.07
    9:0.23
    10:0.02
    11:0.02
    Negative Logits
     Riley
    -4.12
     Damian
    -3.71
    Dam
    -3.54
     Olivia
    -3.47
     Boyle
    -3.46
    iframe
    -3.45
    Detroit
    -3.39
     Foley
    -3.38
     Lima
    -3.37
     Accord
    -3.36
    POSITIVE LOGITS
     SS
    10.49
    SS
    8.49
    ss
    5.84
     ss
    5.64
     Auschwitz
    4.60
     DS
    4.20
     SR
    4.11
     GS
    4.05
     sshd
    3.99
     Zy
    3.99
    Activations Density 0.003%

    No Known Activations