© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 276
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "will" and phrases indicating future actions or commitments

    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
    1:0.34
    2:0.07
    3:0.06
    4:0.03
    5:0.04
    6:0.05
    7:0.04
    8:0.03
    9:0.13
    10:0.05
    11:0.03
    Negative Logits
    ibrary
    -2.93
    azo
    -2.76
    isu
    -2.74
     alternative
    -2.59
     Previously
    -2.57
    ATER
    -2.51
    arted
    -2.46
     裏覚醒
    -2.46
    �士
    -2.45
    の�
    -2.44
    POSITIVE LOGITS
    Keep
    4.72
    keep
    4.52
     keep
    4.36
     Keep
    4.21
    Keeping
    3.99
    keeping
    3.93
     keeps
    3.81
     kept
    3.66
     keeping
    3.49
     Keeping
    3.42
    Activations Density 0.003%

    No Known Activations