© 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. 10-ATT-KK
    6. 15230
    Prev
    Next
    INDEX
    Explanations

    references to decision-making and action steps related to community projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.19
    1:0.08
    2:0.07
    3:0.03
    4:0.04
    5:0.03
    6:0.10
    7:0.08
    8:0.03
    9:0.05
    10:0.17
    11:0.07
    Negative Logits
    LG
    -3.20
     Bentley
    -2.95
     Ghana
    -2.85
    odium
    -2.75
     OU
    -2.74
     rg
    -2.71
     LG
    -2.67
    amba
    -2.66
    Sa
    -2.65
    ynchronous
    -2.62
    POSITIVE LOGITS
     Pier
    9.55
     pier
    7.88
    Pir
    5.13
     Pirate
    4.88
     Piercing
    4.61
     Pir
    4.51
     Pirates
    4.27
     Stein
    4.24
     piercing
    4.08
     Poe
    3.90
    Activations Density 0.003%

    No Known Activations