© 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. 2982
    Prev
    Next
    INDEX
    Explanations

    statements regarding outcomes or fallout from significant events

    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
    0:0.04
    1:0.40
    2:0.07
    3:0.07
    4:0.05
    5:0.05
    6:0.04
    7:0.05
    8:0.03
    9:0.07
    10:0.03
    11:0.04
    Negative Logits
     quadru
    -2.52
     necks
    -2.41
    ixture
    -2.40
    arming
    -2.36
    alli
    -2.29
    mage
    -2.29
    roy
    -2.27
     slump
    -2.26
    ngth
    -2.25
    raltar
    -2.25
    POSITIVE LOGITS
    what
    5.57
     what
    5.25
     WHAT
    4.91
    What
    4.89
     What
    4.83
    why
    4.23
    WHAT
    4.23
     whats
    4.23
     WHY
    3.95
     why
    3.84
    Activations Density 0.045%

    No Known Activations