© 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. 19692
    Prev
    Next
    INDEX
    Explanations

    punctuation and certain characters

    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
    0:0.08
    1:0.04
    2:0.06
    3:0.04
    4:0.04
    5:0.04
    6:0.24
    7:0.05
    8:0.08
    9:0.20
    10:0.03
    11:0.05
    Negative Logits
     Martinez
    -4.01
    Uber
    -3.89
    Compan
    -3.86
     Peninsula
    -3.72
    HUD
    -3.71
     Samson
    -3.70
    itar
    -3.68
    Bat
    -3.67
     bay
    -3.65
    ppo
    -3.62
    POSITIVE LOGITS
     Cre
    8.67
    Cre
    7.25
    cre
    6.39
     cre
    6.16
     CRE
    4.72
     Tre
    4.25
     Cream
    3.83
     Cro
    3.72
     Creep
    3.60
    CRE
    3.60
    Activations Density 0.001%

    No Known Activations