© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 34481
    Prev
    Next
    INDEX
    Explanations

    phrases and structures that include the word "of."

    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
    0:0.02
    1:0.01
    2:0.06
    3:0.04
    4:0.20
    5:0.03
    6:0.02
    7:0.32
    8:0.02
    9:0.03
    10:0.07
    11:0.13
    Negative Logits
    WARD
    -1.55
     envy
    -1.36
    oiler
    -1.23
    ammed
    -1.23
     smelled
    -1.21
     strat
    -1.21
     quake
    -1.20
     mimic
    -1.20
     accompan
    -1.19
     precip
    -1.18
    POSITIVE LOGITS
    profits
    1.69
    isoft
    1.67
    Org
    1.62
     Productions
    1.55
    rams
    1.39
    kit
    1.37
     Horizons
    1.34
     Printing
    1.32
    ojure
    1.25
     Publishers
    1.25
    Activations Density 0.001%

    No Known Activations