© 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. 16431
    Prev
    Next
    INDEX
    Explanations

    instances of the word "A" and analyzes punctuation usage

    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
    0:0.06
    1:0.04
    2:0.08
    3:0.03
    4:0.08
    5:0.04
    6:0.19
    7:0.08
    8:0.06
    9:0.19
    10:0.03
    11:0.06
    Negative Logits
    ivic
    -4.21
     calcul
    -3.58
    ilit
    -3.49
    iris
    -3.36
    ipl
    -3.35
     Icar
    -3.22
     leaf
    -3.20
     Ll
    -3.20
    ivation
    -3.18
     perimeter
    -3.13
    POSITIVE LOGITS
     Franken
    9.33
    Frank
    5.79
     Twe
    4.34
     Archdemon
    4.17
     Cosby
    4.04
     Frank
    4.03
     Schumer
    3.92
     Franklin
    3.88
     Stras
    3.86
     Kavanaugh
    3.85
    Activations Density 0.001%

    No Known Activations