© 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. 8184
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols at the end 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
    0:0.11
    1:0.05
    2:0.13
    3:0.05
    4:0.03
    5:0.04
    6:0.12
    7:0.12
    8:0.04
    9:0.04
    10:0.15
    11:0.05
    Negative Logits
     Benson
    -3.60
     Doc
    -3.18
     Mant
    -3.06
    Doc
    -2.90
     Mig
    -2.86
    hemat
    -2.78
     Cap
    -2.78
     Haz
    -2.67
     Cummings
    -2.65
     doc
    -2.63
    POSITIVE LOGITS
     KR
    9.09
    KR
    7.68
    kr
    4.54
     KH
    4.52
     KL
    4.26
     CHR
    4.22
    LR
    3.81
     KD
    3.75
     KN
    3.74
     LR
    3.70
    Activations Density 0.002%

    No Known Activations