© 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. 5-ATT-KK
    11. 28773
    Prev
    Next
    INDEX
    Explanations

    names and affiliations of scientific authors or contributors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    2:0.07
    3:0.06
    4:0.07
    5:0.03
    6:0.06
    7:0.35
    8:0.04
    9:0.04
    10:0.09
    11:0.07
    Negative Logits
    coins
    -1.58
     cher
    -1.56
    ships
    -1.55
    userc
    -1.51
    Whe
    -1.50
     expectancy
    -1.49
     Finished
    -1.48
    Decre
    -1.48
     Likes
    -1.47
     Mania
    -1.46
    POSITIVE LOGITS
    ctor
    1.84
    ithmetic
    1.79
    tyard
    1.77
    aphael
    1.75
    ilial
    1.65
    heses
    1.63
    olkien
    1.60
    aram
    1.60
    afi
    1.56
    umat
    1.56
    Activations Density 0.001%

    No Known Activations