© 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. 9-ATT-KK
    11. 8153
    Prev
    Next
    INDEX
    Explanations

    references to locations and associated images

    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
    0:0.08
    1:0.03
    2:0.03
    3:0.07
    4:0.05
    5:0.06
    6:0.04
    7:0.41
    8:0.07
    9:0.02
    10:0.06
    11:0.02
    Negative Logits
     Lima
    -2.82
     Islamabad
    -2.68
     Canberra
    -2.56
     Baghdad
    -2.54
     Beng
    -2.50
     Kabul
    -2.41
     Ankara
    -2.38
     Jakarta
    -2.27
     Antioch
    -2.25
     ours
    -2.22
    POSITIVE LOGITS
    pmwiki
    2.96
    wcs
    2.64
    ergy
    2.58
    Getty
    2.57
    dro
    2.40
    oresc
    2.36
    aughs
    2.29
    yright
    2.23
     offic
    2.23
    aneers
    2.20
    Activations Density 0.011%

    No Known Activations