© 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. 10-ATT-KK
    11. 9797
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically periods and commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.14
    2:0.10
    3:0.07
    4:0.05
    5:0.02
    6:0.13
    7:0.10
    8:0.03
    9:0.04
    10:0.10
    11:0.07
    Negative Logits
    qus
    -2.55
    orth
    -2.54
    odan
    -2.53
     derby
    -2.53
     mast
    -2.48
     cave
    -2.42
    dash
    -2.40
    adan
    -2.40
    psons
    -2.39
    usra
    -2.38
    POSITIVE LOGITS
    Chance
    6.87
     Chance
    6.63
    chance
    4.20
     Chancellor
    3.55
     Gamble
    3.28
     Lon
    3.06
     Charm
    2.99
     Pace
    2.96
     Lifetime
    2.78
     Jimmy
    2.74
    Activations Density 0.000%

    No Known Activations