© 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. 16185
    Prev
    Next
    INDEX
    Explanations

    elements of dialogue and interaction

    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
    1:0.08
    2:0.12
    3:0.05
    4:0.03
    5:0.03
    6:0.09
    7:0.11
    8:0.02
    9:0.05
    10:0.16
    11:0.06
    Negative Logits
     Bolshe
    -2.79
    Maria
    -2.70
     chlor
    -2.59
     ans
    -2.59
     trivia
    -2.58
     GA
    -2.56
    Pan
    -2.53
    Gaza
    -2.52
     Slov
    -2.52
     refriger
    -2.51
    POSITIVE LOGITS
     Wiley
    9.18
     Wy
    4.17
     Blackwell
    3.90
     Riley
    3.68
     Wad
    3.60
     Fuj
    3.45
     Pearson
    3.44
     Finch
    3.37
     Drake
    3.35
    iley
    3.27
    Activations Density 0.001%

    No Known Activations