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. 10-ATT-KK
    6. 14563
    Prev
    Next
    INDEX
    Explanations

    references to various forms of art

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.02
    2:0.04
    3:0.03
    4:0.11
    5:0.02
    6:0.02
    7:0.42
    8:0.01
    9:0.03
    10:0.02
    11:0.15
    Negative Logits
    ��
    -2.77
    Admin
    -2.40
    Art
    -2.37
    agen
    -2.26
    admin
    -2.20
     Art
    -2.14
     GC
    -2.13
    art
    -2.07
    aston
    -2.06
     Admin
    -2.02
    POSITIVE LOGITS
    McC
    2.37
     McCabe
    2.33
     McC
    2.24
     Joyce
    2.23
     Vietnamese
    2.19
     McCorm
    2.07
     specialization
    2.05
     Longh
    2.03
     Mississippi
    2.02
     Mississ
    1.98
    Activations Density 0.097%

    No Known Activations