© 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. 9468
    Prev
    Next
    INDEX
    Explanations

    phrases related to online social interactions or networking

    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
    0:0.02
    1:0.02
    2:0.02
    3:0.03
    4:0.18
    5:0.02
    6:0.02
    7:0.43
    8:0.12
    9:0.03
    10:0.03
    11:0.03
    Negative Logits
    LinkedIn
    -4.37
     LinkedIn
    -3.60
     Lamb
    -3.48
     Liverpool
    -3.33
     Merlin
    -3.24
     Berk
    -3.18
     Medina
    -3.07
     LIM
    -3.07
     LU
    -3.04
     Emerson
    -2.94
    POSITIVE LOGITS
    Iv
    3.18
    nos
    3.15
    Sav
    3.12
     Savannah
    3.10
    vich
    3.02
    Wal
    2.78
     Scha
    2.76
    querade
    2.74
    Cos
    2.73
    uch
    2.73
    Activations Density 0.001%

    No Known Activations