© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 15956
    Prev
    Next
    INDEX
    Explanations

    questions that provoke self-reflection or hypothetical scenarios

    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
    1:0.10
    2:0.23
    3:0.08
    4:0.08
    5:0.08
    6:0.03
    7:0.10
    8:0.04
    9:0.03
    10:0.09
    11:0.04
    Negative Logits
     flare
    -2.35
    itton
    -2.33
    rity
    -2.26
     sidel
    -2.17
    osta
    -2.11
     Katy
    -2.08
     groove
    -2.04
     overhe
    -2.04
     SIG
    -2.02
     calibration
    -2.01
    POSITIVE LOGITS
     Would
    3.96
    Imagine
    3.67
    Would
    3.52
     Imagine
    3.25
     hypothetical
    3.19
    Human
    3.04
     Suppose
    3.02
     Wouldn
    2.89
    would
    2.74
    enario
    2.72
    Activations Density 0.049%

    No Known Activations