© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 8687
    Prev
    Next
    INDEX
    Explanations

    scheduling details and references to specific dates and events

    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
    0:0.03
    1:0.04
    2:0.06
    3:0.46
    4:0.04
    5:0.04
    6:0.05
    7:0.07
    8:0.03
    9:0.05
    10:0.04
    11:0.04
    Negative Logits
    izoph
    -2.76
     Acquisition
    -2.35
    2006
    -2.21
    ographies
    -2.18
    uct
    -2.15
    idency
    -2.14
    2007
    -2.14
    iasis
    -2.10
    Balt
    -2.10
    gha
    -2.06
    POSITIVE LOGITS
     Sunday
    7.90
     Saturday
    7.88
     Friday
    7.55
    Sunday
    7.33
    Saturday
    7.27
     Thursday
    7.16
     Monday
    7.15
    Friday
    6.99
     Wednesday
    6.97
    Monday
    6.82
    Activations Density 0.614%

    No Known Activations