© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 21925
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas and periods

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.04
    2:0.08
    3:0.04
    4:0.06
    5:0.04
    6:0.24
    7:0.06
    8:0.07
    9:0.15
    10:0.05
    11:0.04
    Negative Logits
     toe
    -3.25
    enegger
    -3.21
     anchor
    -3.19
    anne
    -3.19
     Anderson
    -3.18
     Arnold
    -3.17
     Gravity
    -3.15
    angan
    -3.15
    anse
    -3.06
     CGI
    -3.06
    POSITIVE LOGITS
     Rab
    9.79
     rab
    7.36
     Barn
    5.20
     Rabb
    4.95
     Rabbit
    4.72
    rab
    4.70
     Rac
    4.33
     rac
    4.29
     barn
    4.19
     Rutherford
    4.14
    Activations Density 0.000%

    No Known Activations