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. 7592
    Prev
    Next
    INDEX
    Explanations

    the presence of specific app names and related terms, particularly in the context of functionality and updates

    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
    1:0.03
    2:0.06
    3:0.06
    4:0.06
    5:0.04
    6:0.21
    7:0.03
    8:0.06
    9:0.25
    10:0.04
    11:0.04
    Negative Logits
    annis
    -3.87
     Lois
    -3.76
     vegetable
    -3.47
    icals
    -3.33
    Wil
    -3.27
    ilan
    -3.23
     Robertson
    -3.22
    anes
    -3.18
    iculture
    -3.18
     vegetables
    -3.17
    POSITIVE LOGITS
     Vault
    8.70
    ault
    6.98
     vault
    6.74
    aults
    5.22
     Vaults
    4.69
     Crypt
    3.80
     Dexter
    3.67
     Tomb
    3.60
     Pastebin
    3.59
     Fault
    3.57
    Activations Density 0.000%

    No Known Activations