© 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. 3523
    Prev
    Next
    INDEX
    Explanations

    tokens that represent various forms of numerical or identifying labels

    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
    0:0.09
    1:0.02
    2:0.08
    3:0.03
    4:0.03
    5:0.03
    6:0.17
    7:0.04
    8:0.08
    9:0.33
    10:0.01
    11:0.02
    Negative Logits
    frames
    -3.32
     Roh
    -3.29
    ROM
    -3.19
     Devi
    -3.13
     RAND
    -3.13
     Morty
    -3.12
     Twist
    -3.12
     Iranians
    -3.10
     prism
    -3.06
     Iran
    -3.03
    POSITIVE LOGITS
     Au
    8.27
    au
    7.29
     au
    6.00
     Lau
    5.84
     Hau
    5.80
     Beau
    5.65
     Sau
    5.50
     Tau
    5.48
    AU
    5.40
     Kau
    4.82
    Activations Density 0.004%

    No Known Activations