© 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. 43839
    Prev
    Next
    INDEX
    Explanations

    references to biological processes and mechanisms, especially in the context of disease

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.02
    1:0.02
    2:0.07
    3:0.06
    4:0.12
    5:0.03
    6:0.03
    7:0.34
    8:0.03
    9:0.03
    10:0.11
    11:0.08
    Negative Logits
     accus
    -1.53
    Austral
    -1.51
    �
    -1.51
    Companies
    -1.44
    apest
    -1.42
    ablishment
    -1.41
    hare
    -1.40
    ppa
    -1.36
    arnaev
    -1.35
    addle
    -1.34
    POSITIVE LOGITS
     cellular
    1.71
     Cellular
    1.63
     Calories
    1.51
     enzyme
    1.48
     mitochondrial
    1.47
    growth
    1.46
     fusion
    1.44
     serotonin
    1.44
     caloric
    1.43
     calorie
    1.41
    Activations Density 0.003%

    No Known Activations