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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43312
    Prev
    Next
    INDEX
    Explanations

    prepositions and articles within sentences

    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
    1:0.01
    2:0.12
    3:0.05
    4:0.12
    5:0.03
    6:0.14
    7:0.25
    8:0.03
    9:0.04
    10:0.08
    11:0.05
    Negative Logits
    ickr
    -1.83
    enment
    -1.62
    imir
    -1.60
    weak
    -1.52
    irrel
    -1.50
    ��
    -1.50
    wagen
    -1.50
    destruct
    -1.50
    fect
    -1.47
    anus
    -1.43
    POSITIVE LOGITS
     royalties
    1.71
     Esports
    1.48
    DragonMagazine
    1.46
     Ninja
    1.39
     fares
    1.37
     runtime
    1.37
     workload
    1.37
     commentary
    1.35
     credits
    1.34
     Recommended
    1.34
    Activations Density 0.001%

    No Known Activations