© 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. 9-ATT-KK
    11. 16726
    Prev
    Next
    INDEX
    Explanations

    punctuation and structures related to sentence endings or transitions

    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
    0:0.09
    1:0.02
    2:0.09
    3:0.04
    4:0.05
    5:0.03
    6:0.24
    7:0.05
    8:0.08
    9:0.22
    10:0.02
    11:0.03
    Negative Logits
     Bowman
    -4.04
     Gree
    -3.83
     Fein
    -3.79
     Aurora
    -3.76
     Hawkins
    -3.71
     Glac
    -3.60
     Bows
    -3.49
     Brow
    -3.46
     Rockets
    -3.46
     Hawking
    -3.44
    POSITIVE LOGITS
     Dom
    9.75
    Domin
    9.20
    Dom
    9.14
    dom
    8.05
     Dominic
    7.59
     Domin
    7.58
     domin
    7.39
     dom
    7.28
    DOM
    6.97
     DOM
    5.95
    Activations Density 0.005%

    No Known Activations