© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14031
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and the structure of sentences

    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
    0:0.16
    1:0.08
    2:0.11
    3:0.03
    4:0.03
    5:0.02
    6:0.09
    7:0.14
    8:0.01
    9:0.04
    10:0.18
    11:0.06
    Negative Logits
    エル
    -2.96
    Jews
    -2.65
    ahime
    -2.62
    estine
    -2.58
    Palestinian
    -2.54
    etsk
    -2.52
    Jer
    -2.49
    nv
    -2.49
     chall
    -2.48
    usalem
    -2.45
    POSITIVE LOGITS
     Bates
    8.17
     Berks
    3.74
     Bent
    3.61
     Baker
    3.42
    bart
    3.31
     Buck
    3.24
     Bot
    3.23
     Bos
    3.22
     Benson
    3.19
     Bart
    3.16
    Activations Density 0.001%

    No Known Activations