© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 21633
    Prev
    Next
    INDEX
    Explanations

    end punctuation, specifically periods and quotation marks

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.03
    1:0.04
    2:0.03
    3:0.05
    4:0.13
    5:0.04
    6:0.32
    7:0.06
    8:0.05
    9:0.05
    10:0.06
    11:0.08
    Negative Logits
     Tesla
    -2.92
     Hart
    -2.70
     Thomson
    -2.70
     Ford
    -2.69
     spirit
    -2.67
    Tracker
    -2.64
     Ze
    -2.62
     Sin
    -2.62
     horn
    -2.59
     Spot
    -2.58
    POSITIVE LOGITS
    acco
    3.21
    anches
    3.19
    conserv
    3.18
    aceae
    3.12
    ilies
    3.05
     Juven
    3.02
     Nurs
    3.00
    aii
    2.98
    aund
    2.94
    SPONSORED
    2.90
    Activations Density 0.002%

    No Known Activations