© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 10946
    Prev
    Next
    INDEX
    Explanations

    references to technical specifications of products

    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
    0:0.12
    1:0.03
    2:0.05
    3:0.23
    4:0.04
    5:0.21
    6:0.04
    7:0.04
    8:0.04
    9:0.04
    10:0.06
    11:0.03
    Negative Logits
     endorsements
    -2.11
     spoil
    -1.90
     bidder
    -1.87
     approvals
    -1.84
     heels
    -1.79
     premiums
    -1.78
     nipples
    -1.78
     depreciation
    -1.75
     villains
    -1.75
     margins
    -1.74
    POSITIVE LOGITS
    Desk
    1.97
     Streaming
    1.96
    tein
    1.91
    Aid
    1.87
     Meditation
    1.86
    abo
    1.86
    kt
    1.81
    eton
    1.80
    stice
    1.79
    �
    1.78
    Activations Density 0.267%

    No Known Activations