© 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. 8972
    Prev
    Next
    INDEX
    Explanations

    occurrences of punctuation and specific grammatical structures in the text

    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
    0:0.07
    1:0.02
    2:0.07
    3:0.04
    4:0.04
    5:0.03
    6:0.27
    7:0.03
    8:0.06
    9:0.26
    10:0.03
    11:0.02
    Negative Logits
     comet
    -4.51
     MET
    -3.75
     Comet
    -3.70
     Ridley
    -3.55
     Raiders
    -3.54
     dj
    -3.53
     Bernstein
    -3.51
    Raid
    -3.49
    dq
    -3.48
    omet
    -3.45
    POSITIVE LOGITS
     Grace
    10.62
    Gr
    6.50
     grace
    6.38
    gr
    5.47
     Grimes
    5.16
     Griffith
    5.12
     Grac
    5.01
     Griffin
    4.84
    Joy
    4.49
     Gr
    4.24
    Activations Density 0.001%

    No Known Activations