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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 19223
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the."

    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
    0:0.02
    1:0.01
    2:0.10
    3:0.08
    4:0.16
    5:0.03
    6:0.26
    7:0.08
    8:0.04
    9:0.04
    10:0.07
    11:0.05
    Negative Logits
     uncanny
    -1.35
    龍
    -1.29
     nap
    -1.27
    RET
    -1.25
     FANT
    -1.24
    USS
    -1.23
    の魔
    -1.22
    beard
    -1.22
    QUEST
    -1.21
     squid
    -1.19
    POSITIVE LOGITS
    insula
    1.58
    artifacts
    1.54
    achine
    1.53
     respectively
    1.46
    gallery
    1.45
    estate
    1.44
    pta
    1.41
    iseum
    1.38
    loo
    1.35
    inent
    1.32
    Activations Density 0.001%

    No Known Activations