© 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. 2362
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to commitment and future planning

    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
    0:0.08
    1:0.02
    2:0.05
    3:0.13
    4:0.02
    5:0.07
    6:0.02
    7:0.06
    8:0.02
    9:0.01
    10:0.45
    11:0.02
    Negative Logits
    ゴ
    -1.97
     )]
    -1.88
     plush
    -1.84
    mouth
    -1.81
     rall
    -1.79
    orest
    -1.78
    phies
    -1.78
     "$:/
    -1.76
     cushion
    -1.74
    AFTA
    -1.71
    POSITIVE LOGITS
     aloud
    2.40
     before
    2.18
    choice
    2.03
    evaluate
    2.02
     twice
    2.00
    before
    1.99
    thinkable
    1.98
     alternatives
    1.98
    loo
    1.98
     differently
    1.93
    Activations Density 0.133%

    No Known Activations