© 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. 5-ATT-KK
    11. 5373
    Prev
    Next
    INDEX
    Explanations

    references to production and quantities related to various sectors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.02
    2:0.05
    3:0.06
    4:0.23
    5:0.04
    6:0.04
    7:0.29
    8:0.02
    9:0.02
    10:0.08
    11:0.08
    Negative Logits
    aimon
    -1.71
    DIT
    -1.66
    externalActionCode
    -1.62
    conservancy
    -1.56
    ospons
    -1.50
    join
    -1.49
    remember
    -1.40
    introdu
    -1.38
    uthor
    -1.36
    avoid
    -1.36
    POSITIVE LOGITS
     batches
    1.72
     usable
    1.62
    eers
    1.51
     surplus
    1.38
     copies
    1.37
     miniature
    1.36
     brill
    1.35
     ful
    1.33
     tonnes
    1.29
     incom
    1.28
    Activations Density 0.042%

    No Known Activations