© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 19709
    Prev
    Next
    INDEX
    Explanations

    punctuations, specifically the period

    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
    0:0.07
    1:0.08
    2:0.08
    3:0.07
    4:0.07
    5:0.08
    6:0.08
    7:0.08
    8:0.08
    9:0.09
    10:0.08
    11:0.09
    Negative Logits
     Avalon
    -3.00
     Scythe
    -2.79
     VPN
    -2.78
     Shim
    -2.71
     Pol
    -2.67
     Psy
    -2.64
     Cyber
    -2.60
     Umb
    -2.58
     Cerberus
    -2.56
     Nek
    -2.54
    POSITIVE LOGITS
    elight
    2.93
    Louis
    2.78
    istine
    2.64
    umbers
    2.62
    Title
    2.57
    erous
    2.51
    ogan
    2.50
    heid
    2.48
    TPPStreamerBot
    2.43
    arth
    2.43
    Activations Density 0.000%

    No Known Activations