Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14693
    Prev
    Next
    INDEX
    Explanations

    references to specific days, times, and news-related entities

    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
    1:0.02
    2:0.02
    3:0.07
    4:0.06
    5:0.17
    6:0.02
    7:0.10
    8:0.02
    9:0.36
    10:0.02
    11:0.05
    Negative Logits
    Cause
    -2.02
     nutshell
    -2.01
    ={
    -2.01
     begin
    -1.99
    Plot
    -1.98
     proclaim
    -1.94
    izo
    -1.84
    cause
    -1.84
     evolves
    -1.80
     incent
    -1.78
    POSITIVE LOGITS
     herself
    2.48
     himself
    2.36
    ELS
    2.10
     yesterday
    2.10
    ONDON
    2.09
     she
    2.07
     his
    2.06
    EPA
    1.99
    龍喚士
    1.98
     separately
    1.98
    Activations Density 0.007%

    No Known Activations