© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 21348
    Prev
    Next
    INDEX
    Explanations

    specific dates and events related to news articles and announcements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.04
    2:0.08
    3:0.08
    4:0.03
    5:0.09
    6:0.03
    7:0.04
    8:0.22
    9:0.11
    10:0.08
    11:0.04
    Negative Logits
     narr
    -1.46
     temperament
    -1.34
     glim
    -1.34
     coefficients
    -1.33
     todd
    -1.27
     pudding
    -1.24
     algebra
    -1.24
     extraord
    -1.23
     elector
    -1.22
     neigh
    -1.20
    POSITIVE LOGITS
    untled
    1.47
     Funding
    1.36
    Reloaded
    1.35
     Opportun
    1.35
     Agenda
    1.34
    Site
    1.33
    until
    1.33
     Furious
    1.32
     Deadline
    1.26
    angering
    1.25
    Activations Density 0.014%

    No Known Activations