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. 9-ATT-KK
    6. 3037
    Prev
    Next
    INDEX
    Explanations

    references to social media sharing and interaction metrics

    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
    0:0.02
    1:0.22
    2:0.02
    3:0.09
    4:0.04
    5:0.18
    6:0.01
    7:0.17
    8:0.02
    9:0.01
    10:0.17
    11:0.02
    Negative Logits
    �
    -2.30
    pool
    -2.08
    cules
    -2.03
     vibrant
    -1.95
    illary
    -1.95
    �
    -1.94
     thriving
    -1.94
    olated
    -1.91
    Social
    -1.89
    leans
    -1.89
    POSITIVE LOGITS
     thence
    2.36
    oub
    2.35
     Flavoring
    2.20
     Petersen
    2.18
     Aires
    2.17
    Reply
    2.09
     Bentley
    2.08
    phrine
    2.03
     Stur
    1.99
     GEAR
    1.97
    Activations Density 0.002%

    No Known Activations