© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 10851
    Prev
    Next
    INDEX
    Explanations

    guidelines and considerations related to tiling and existing tile conditions

    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
    0:0.16
    1:0.04
    2:0.08
    3:0.06
    4:0.06
    5:0.04
    6:0.18
    7:0.03
    8:0.08
    9:0.16
    10:0.03
    11:0.03
    Negative Logits
    avez
    -4.18
     bourbon
    -3.92
    ascript
    -3.87
    Hug
    -3.69
     bour
    -3.68
     Bourbon
    -3.66
     motorcycle
    -3.59
    iatus
    -3.59
     Benson
    -3.58
     VMware
    -3.48
    POSITIVE LOGITS
     tiles
    9.34
     tile
    8.52
     Tile
    8.42
    Tile
    8.26
    tile
    7.50
     Tur
    4.18
    Poké
    4.04
     mosaic
    4.00
     Tib
    3.93
     Tet
    3.90
    Activations Density 0.005%

    No Known Activations