© 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. 239
    Prev
    Next
    INDEX
    Explanations

    references to images, photographs, or visual content

    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
    0:0.04
    1:0.02
    2:0.03
    3:0.07
    4:0.08
    5:0.06
    6:0.07
    7:0.42
    8:0.07
    9:0.02
    10:0.04
    11:0.04
    Negative Logits
    <|endoftext|>
    -2.73
    ________________
    -2.63
    Advertisements
    -2.62
     Logged
    -2.60
     NCT
    -2.43
     ---------
    -2.33
     Admin
    -2.31
     Views
    -2.30
     Moons
    -2.28
    ________________________
    -2.28
    POSITIVE LOGITS
    hello
    2.74
    cow
    2.27
    pictured
    2.27
    onge
    2.24
    Britain
    2.20
    tto
    2.20
    raltar
    2.19
     tyres
    2.06
    ffield
    2.04
    style
    2.01
    Activations Density 0.166%

    No Known Activations