© 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. 9563
    Prev
    Next
    INDEX
    Explanations

    sections and headings related to reports or estimates on expenditures and regulations

    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
    1:0.15
    2:0.05
    3:0.06
    4:0.05
    5:0.04
    6:0.13
    7:0.04
    8:0.04
    9:0.26
    10:0.04
    11:0.05
    Negative Logits
    atre
    -3.28
    prus
    -2.92
     Flowers
    -2.90
    CHR
    -2.82
    ipolar
    -2.81
    PN
    -2.81
    BOX
    -2.76
     Tub
    -2.75
     Duffy
    -2.73
     Nic
    -2.73
    POSITIVE LOGITS
    imates
    4.28
     estimate
    4.20
     estimated
    4.17
     estimation
    4.14
     estimates
    4.01
     underestimate
    3.91
     Estimates
    3.86
     underest
    3.77
    imate
    3.71
    Est
    3.66
    Activations Density 0.000%

    No Known Activations