© 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. 13422
    Prev
    Next
    INDEX
    Explanations

    terms related to telecommunications infrastructure and their operational context

    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
    0:0.15
    1:0.10
    2:0.08
    3:0.03
    4:0.03
    5:0.03
    6:0.11
    7:0.13
    8:0.04
    9:0.04
    10:0.15
    11:0.04
    Negative Logits
     Fior
    -3.58
     Salvador
    -3.53
     Mayo
    -3.27
    ザ
    -3.06
     Dia
    -2.90
     latex
    -2.74
     Cohn
    -2.71
     Rae
    -2.70
     Moe
    -2.67
     Scal
    -2.65
    POSITIVE LOGITS
     BT
    7.30
    BT
    6.21
    bt
    4.01
     Belg
    3.62
    LT
    3.25
    lt
    3.19
    Nit
    3.08
     TT
    3.05
    gt
    3.02
     MT
    2.96
    Activations Density 0.005%

    No Known Activations