© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 10203
    Prev
    Next
    INDEX
    Explanations

    mentions of digital content file sizes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.14
    3:0.15
    4:0.13
    5:0.03
    6:0.05
    7:0.12
    8:0.05
    9:0.07
    10:0.07
    11:0.10
    Negative Logits
     神
    -1.25
    î
    -1.19
     medic
    -1.18
    rahim
    -1.18
    onom
    -1.18
    ulton
    -1.17
    istrate
    -1.17
    ixed
    -1.17
     independents
    -1.15
    ALSE
    -1.14
    POSITIVE LOGITS
    emonium
    1.36
    Event
    1.34
    BuyableInstoreAndOnline
    1.29
    Setup
    1.25
     rall
    1.22
     Corsair
    1.22
    rawdownloadcloneembedreportprint
    1.19
    ####
    1.18
     Uncharted
    1.17
    Posted
    1.16
    Activations Density 0.000%

    No Known Activations