© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 5472
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation marks and their frequency of use

    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
    0:0.03
    1:0.21
    2:0.03
    3:0.04
    4:0.08
    5:0.05
    6:0.03
    7:0.35
    8:0.02
    9:0.03
    10:0.04
    11:0.04
    Negative Logits
    ahime
    -2.77
    ayan
    -2.58
     Afgh
    -2.47
    learn
    -2.43
    gae
    -2.43
    kr
    -2.26
    orea
    -2.23
    PE
    -2.20
    cair
    -2.20
     Kand
    -2.17
    POSITIVE LOGITS
    Third
    7.83
     third
    6.59
    Fourth
    6.46
     Third
    6.24
     fourth
    5.33
    third
    5.08
     Lastly
    4.60
    fourth
    4.56
    Finally
    4.55
     fifth
    4.54
    Activations Density 0.017%

    No Known Activations