© 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. 13867
    Prev
    Next
    INDEX
    Explanations

    video game consoles and their compatibility across different platforms

    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
    0:0.06
    1:0.03
    2:0.04
    3:0.07
    4:0.08
    5:0.17
    6:0.03
    7:0.08
    8:0.10
    9:0.14
    10:0.04
    11:0.09
    Negative Logits
    cffffcc
    -2.89
    inventoryQuantity
    -2.83
     recalls
    -2.61
    soDeliveryDate
    -2.55
    ieri
    -2.42
     meaningless
    -2.42
    andum
    -2.40
     coincided
    -2.31
     suddenly
    -2.28
     devast
    -2.27
    POSITIVE LOGITS
     720
    2.61
     FAT
    2.60
    Xbox
    2.43
    DOWN
    2.41
     INCLUD
    2.38
    я
    2.35
    ®,
    2.34
     Mono
    2.30
    Linux
    2.29
     SUN
    2.28
    Activations Density 0.007%

    No Known Activations