© 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. 8288
    Prev
    Next
    INDEX
    Explanations

    mentions of significant environmental or ecological changes

    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
    0:0.04
    1:0.05
    2:0.15
    3:0.12
    4:0.12
    5:0.08
    6:0.04
    7:0.10
    8:0.05
    9:0.10
    10:0.04
    11:0.06
    Negative Logits
     foil
    -2.08
     dudes
    -2.04
     shuffle
    -1.95
     ambassadors
    -1.89
     420
    -1.88
     sprung
    -1.85
     kale
    -1.85
     ladies
    -1.84
     pigeon
    -1.84
     1600
    -1.84
    POSITIVE LOGITS
    ÃÂ
    3.80
    �
    3.44
    �
    3.16
    �
    3.04
    �
    3.04
    �
    3.01
    �
    2.97
    �
    2.95
    �
    2.92
    �
    2.91
    Activations Density 0.511%

    No Known Activations