© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 35442
    Prev
    Next
    INDEX
    Explanations

    financial statistics and trends

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.03
    2:0.05
    3:0.09
    4:0.06
    5:0.09
    6:0.05
    7:0.02
    8:0.09
    9:0.11
    10:0.18
    11:0.14
    Negative Logits
     Milo
    -1.27
     bounty
    -1.25
     undert
    -1.23
     estab
    -1.18
     accomp
    -1.17
     boiler
    -1.16
     comr
    -1.15
     lad
    -1.08
    ascript
    -1.06
     enlightenment
    -1.06
    POSITIVE LOGITS
    Average
    1.37
    Source
    1.33
    Image
    1.31
    photos
    1.29
    Phones
    1.29
     ⓘ
    1.28
     Views
    1.28
     Photos
    1.27
    Screenshot
    1.26
    Weak
    1.26
    Activations Density 0.314%

    No Known Activations