© 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. 16124
    Prev
    Next
    INDEX
    Explanations

    references to significant events or notable points of interest related to Istanbul

    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
    0:0.07
    1:0.08
    2:0.08
    3:0.03
    4:0.03
    5:0.01
    6:0.22
    7:0.08
    8:0.03
    9:0.04
    10:0.25
    11:0.03
    Negative Logits
    orian
    -3.64
    ォ
    -3.44
    lehem
    -3.35
    ighth
    -3.33
    Rated
    -3.23
    cliffe
    -3.12
    ouver
    -3.09
    bler
    -3.08
    Marginal
    -3.06
    erness
    -3.02
    POSITIVE LOGITS
     Ag
    9.54
    Ag
    8.16
     AG
    7.91
     ag
    6.27
    AG
    6.00
    ag
    5.77
     Og
    4.57
    agg
    4.14
     agre
    4.13
     Sag
    4.03
    Activations Density 0.030%

    No Known Activations