© 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. 40575
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to patent applications and intellectual property

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    1:0.01
    2:0.05
    3:0.05
    4:0.04
    5:0.04
    6:0.03
    7:0.08
    8:0.02
    9:0.05
    10:0.40
    11:0.16
    Negative Logits
     worsh
    -1.43
     glim
    -1.41
     Zombies
    -1.40
    eless
    -1.39
    usterity
    -1.37
    Mods
    -1.35
    ヘ
    -1.34
    politics
    -1.34
     sleeps
    -1.33
    morrow
    -1.33
    POSITIVE LOGITS
     Patent
    1.65
     patent
    1.56
     memorandum
    1.43
     outlining
    1.42
     handwritten
    1.38
     executed
    1.38
     elaborate
    1.37
     filings
    1.35
     preliminary
    1.28
     detailing
    1.28
    Activations Density 0.030%

    No Known Activations