© 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. 10-ATT-KK
    11. 7842
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to organizational structures and challenges in workflows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.03
    2:0.03
    3:0.04
    4:0.08
    5:0.50
    6:0.02
    7:0.03
    8:0.01
    9:0.10
    10:0.01
    11:0.04
    Negative Logits
    now
    -4.25
     now
    -4.10
     NOW
    -3.85
     presently
    -3.62
     since
    -3.52
    since
    -3.26
    currently
    -3.13
     Now
    -3.09
    today
    -3.05
     currently
    -2.99
    POSITIVE LOGITS
     spills
    3.36
     drown
    3.35
     distract
    3.24
     overwhel
    3.23
     accidentally
    3.20
     slips
    3.18
     fails
    3.13
     surprises
    3.05
     pops
    3.02
     might
    2.97
    Activations Density 0.244%

    No Known Activations