© 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. 15627
    Prev
    Next
    INDEX
    Explanations

    references to monetary values or financial figures

    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
    0:0.03
    1:0.07
    2:0.21
    3:0.04
    4:0.06
    5:0.04
    6:0.05
    7:0.17
    8:0.09
    9:0.05
    10:0.10
    11:0.03
    Negative Logits
     Tomas
    -2.48
     Tib
    -2.46
     Hash
    -2.30
     Cth
    -2.27
     Clause
    -2.24
     Hatt
    -2.22
     Hath
    -2.22
     Kop
    -2.21
     princ
    -2.19
     Principle
    -2.16
    POSITIVE LOGITS
    -$
    3.94
    .$
    3.77
    $
    3.47
     $
    3.10
    /$
    3.02
    ⓘ
    3.00
     [+
    2.96
    £
    2.94
    =$
    2.91
    advertising
    2.89
    Activations Density 0.043%

    No Known Activations