© 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. 9-ATT-KK
    11. 14603
    Prev
    Next
    INDEX
    Explanations

    information related to product launches and comparisons in the technology sector

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.17
    1:0.03
    2:0.09
    3:0.06
    4:0.04
    5:0.08
    6:0.08
    7:0.05
    8:0.24
    9:0.07
    10:0.02
    11:0.02
    Negative Logits
     Lann
    -4.07
     SNP
    -3.67
    estern
    -3.58
     Braves
    -3.54
     Scotland
    -3.34
     BP
    -3.34
    Scotland
    -3.33
     Edinburgh
    -3.21
     Rove
    -3.20
     Byrd
    -3.16
    POSITIVE LOGITS
     HTC
    8.98
     Vive
    4.92
     Nguyen
    4.84
     headset
    4.84
     handset
    4.73
     Taiwanese
    4.71
     Droid
    4.67
     OnePlus
    4.54
    guyen
    4.43
     Qualcomm
    4.37
    Activations Density 0.011%

    No Known Activations