© 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. 18000
    Prev
    Next
    INDEX
    Explanations

    punctuations and sentence-ending structures

    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
    0:0.08
    1:0.02
    2:0.05
    3:0.02
    4:0.08
    5:0.03
    6:0.27
    7:0.05
    8:0.08
    9:0.19
    10:0.02
    11:0.05
    Negative Logits
     Hispan
    -3.84
    ilan
    -3.66
     CSS
    -3.63
     Franken
    -3.47
     Stras
    -3.46
     regress
    -3.35
     Paras
    -3.31
    POR
    -3.23
     capac
    -3.22
    SPA
    -3.22
    POSITIVE LOGITS
     Boyd
    11.14
    oyd
    5.67
     Bennett
    5.26
     Boyle
    4.71
     Bryant
    4.65
     Clancy
    4.64
     Barrett
    4.38
     Browne
    4.33
     Booth
    4.23
     Baz
    4.18
    Activations Density 0.002%

    No Known Activations