© 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. 9240
    Prev
    Next
    INDEX
    Explanations

    instances of code or programming terminology related to experimentation and variable manipulation

    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
    0:0.03
    1:0.02
    2:0.10
    3:0.34
    4:0.06
    5:0.04
    6:0.03
    7:0.04
    8:0.06
    9:0.05
    10:0.09
    11:0.09
    Negative Logits
    "]=>
    -1.99
    ".[
    -1.73
    "},
    -1.60
    inventoryQuantity
    -1.59
    ][/
    -1.58
    "]
    -1.57
    ."[
    -1.57
     Cosponsors
    -1.57
     regrets
    -1.56
    Alien
    -1.51
    POSITIVE LOGITS
    urdy
    1.60
    haired
    1.58
     THEN
    1.55
    itaire
    1.55
    anus
    1.53
    lication
    1.48
     descended
    1.45
     drunk
    1.45
    pez
    1.39
    miah
    1.35
    Activations Density 0.042%

    No Known Activations