© 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. 10-ATT-KK
    11. 20224
    Prev
    Next
    INDEX
    Explanations

    textual references to time and dates

    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
    0:0.16
    1:0.06
    2:0.12
    3:0.14
    4:0.04
    5:0.02
    6:0.08
    7:0.10
    8:0.01
    9:0.04
    10:0.14
    11:0.04
    Negative Logits
     Ulster
    -3.15
    �醒
    -3.04
    LU
    -2.96
    Cy
    -2.85
    Rog
    -2.81
    uliffe
    -2.79
    �
    -2.74
    LT
    -2.69
    bg
    -2.59
    闘
    -2.58
    POSITIVE LOGITS
     Maya
    9.46
     Prescott
    4.01
     Mesa
    3.91
     Mats
    3.82
     Gems
    3.61
     Willow
    3.48
     Jasper
    3.45
     Mara
    3.41
     pearl
    3.37
     Phoenix
    3.36
    Activations Density 0.001%

    No Known Activations