© 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. 8324
    Prev
    Next
    INDEX
    Explanations

    phrases expressing ongoing actions or conditions related to various subjects

    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
    0:0.11
    1:0.06
    2:0.05
    3:0.06
    4:0.02
    5:0.03
    6:0.13
    7:0.03
    8:0.02
    9:0.37
    10:0.04
    11:0.02
    Negative Logits
    atan
    -3.93
    alore
    -3.92
    Sund
    -3.84
     Chaff
    -3.72
    ANN
    -3.53
    aza
    -3.50
    adh
    -3.50
    Mos
    -3.48
    Ban
    -3.47
     Mun
    -3.37
    POSITIVE LOGITS
     Writer
    6.18
     Writers
    6.06
     writers
    5.89
    writing
    5.83
     Writing
    5.81
    writer
    5.79
    write
    5.77
     write
    5.71
    writers
    5.69
     writing
    5.68
    Activations Density 0.013%

    No Known Activations