© 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. 19252
    Prev
    Next
    INDEX
    Explanations

    quotes or dialogue from individuals within a narrative 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
    0:0.05
    1:0.06
    2:0.15
    3:0.05
    4:0.03
    5:0.02
    6:0.03
    7:0.09
    8:0.03
    9:0.04
    10:0.37
    11:0.03
    Negative Logits
     Ber
    -4.28
    Ber
    -3.03
     Roh
    -3.01
     coh
    -2.92
     Bots
    -2.88
     dh
    -2.85
     GER
    -2.84
     Koh
    -2.70
     Beth
    -2.69
     ber
    -2.65
    POSITIVE LOGITS
     X
    10.24
    X
    8.63
     x
    5.74
     XX
    5.53
    XM
    5.45
     XI
    5.20
     XV
    5.13
     XXX
    5.10
    XX
    5.10
    x
    5.06
    Activations Density 0.206%

    No Known Activations