© 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. 7574
    Prev
    Next
    INDEX
    Explanations

    features related to connectivity and communication technology

    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
    0:0.08
    1:0.05
    2:0.03
    3:0.04
    4:0.14
    5:0.05
    6:0.05
    7:0.32
    8:0.02
    9:0.05
    10:0.05
    11:0.08
    Negative Logits
    ModLoader
    -2.77
     NRS
    -2.64
    natureconservancy
    -2.54
     Fiber
    -2.46
    uds
    -2.38
     Vikings
    -2.38
    wine
    -2.35
     telecom
    -2.34
     NBN
    -2.24
    NFL
    -2.22
    POSITIVE LOGITS
     Mir
    2.76
    Pic
    2.35
    cher
    2.29
     cinem
    2.24
     Cand
    2.20
    Movie
    2.19
     Cinema
    2.18
     POP
    2.12
    alyst
    2.10
    actory
    2.07
    Activations Density 0.017%

    No Known Activations