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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 20490
    Prev
    Next
    INDEX
    Explanations

    content related to blogging and content creation

    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
    0:0.34
    1:0.01
    2:0.11
    3:0.09
    4:0.02
    5:0.10
    6:0.02
    7:0.07
    8:0.06
    9:0.05
    10:0.04
    11:0.02
    Negative Logits
     Clapper
    -2.64
    HUD
    -2.42
     bluff
    -2.42
    chrom
    -2.37
     Lauder
    -2.32
     PLAY
    -2.30
     PAL
    -2.13
     Casting
    -2.11
     handset
    -2.11
    ��
    -2.10
    POSITIVE LOGITS
     blogging
    5.85
     Blog
    4.82
     blogs
    4.78
    blog
    4.78
     blog
    4.74
     bloggers
    4.63
    blogs
    4.54
    Blog
    4.33
     blogger
    4.15
     posts
    3.98
    Activations Density 0.063%

    No Known Activations