© 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. 12902
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" along with phrases indicating time or conditions

    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
    0:0.05
    1:0.21
    2:0.04
    3:0.06
    4:0.04
    5:0.06
    6:0.08
    7:0.04
    8:0.03
    9:0.27
    10:0.04
    11:0.04
    Negative Logits
     Lur
    -3.59
    cker
    -3.58
    cair
    -3.36
    urtle
    -3.34
    leigh
    -3.32
     DAR
    -3.21
     DAC
    -3.17
    ULAR
    -2.94
     Muller
    -2.88
     Curt
    -2.88
    POSITIVE LOGITS
    past
    5.22
     Past
    5.14
    Past
    4.62
     past
    4.39
    ago
    3.70
    apego
    3.14
     XIII
    3.13
    FY
    3.10
     pastry
    2.97
    Iterator
    2.96
    Activations Density 0.000%

    No Known Activations