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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 7691
    Prev
    Next
    INDEX
    Explanations

    certain past tense verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.08
    2:0.08
    3:0.09
    4:0.07
    5:0.08
    6:0.08
    7:0.09
    8:0.07
    9:0.09
    10:0.08
    11:0.07
    Negative Logits
    onis
    -2.71
     Pars
    -2.71
    odox
    -2.65
    Kay
    -2.58
     Ree
    -2.57
    rag
    -2.43
     Xan
    -2.42
     Zo
    -2.39
    RAW
    -2.39
    ophys
    -2.35
    POSITIVE LOGITS
     shelters
    2.81
     hotels
    2.57
     café
    2.52
     shelter
    2.46
     hotel
    2.36
     spokeswoman
    2.36
     storefront
    2.35
     fixture
    2.31
     pedest
    2.29
    houses
    2.28
    Activations Density 0.000%

    No Known Activations