© 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. 21336
    Prev
    Next
    INDEX
    Explanations

    instances of the word "last" in various contexts

    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
    0:0.08
    1:0.07
    2:0.04
    3:0.05
    4:0.06
    5:0.03
    6:0.14
    7:0.11
    8:0.08
    9:0.04
    10:0.04
    11:0.20
    Negative Logits
     reckoning
    -2.49
     lawyers
    -2.45
     retail
    -2.43
     docs
    -2.39
     deadlines
    -2.35
     fees
    -2.33
     plaintiffs
    -2.29
     attorneys
    -2.29
     lett
    -2.23
     tables
    -2.20
    POSITIVE LOGITS
    thread
    3.21
    Thread
    2.88
    anon
    2.88
     threads
    2.81
     Thread
    2.79
    link
    2.73
     thread
    2.69
     Posts
    2.65
    Link
    2.51
    hei
    2.47
    Activations Density 0.000%

    No Known Activations