© 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. 12322
    Prev
    Next
    INDEX
    Explanations

    references to protocols and their implementation processes

    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
    0:0.10
    1:0.02
    2:0.09
    3:0.06
    4:0.03
    5:0.04
    6:0.18
    7:0.04
    8:0.06
    9:0.26
    10:0.03
    11:0.03
    Negative Logits
     Lily
    -4.61
     Grayson
    -4.01
    Dust
    -3.83
    rys
    -3.81
    aurus
    -3.58
     Fir
    -3.56
     Dustin
    -3.50
     Subaru
    -3.49
     Dunk
    -3.35
     Chevy
    -3.28
    POSITIVE LOGITS
     protocol
    8.06
     Protocol
    7.91
     protocols
    7.86
    prot
    5.94
    Prot
    5.05
     proto
    4.24
    HTTP
    4.12
     RPC
    4.09
     commun
    3.91
     rapport
    3.87
    Activations Density 0.001%

    No Known Activations