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. 3-ATT-KK
    6. 10357
    Prev
    Next
    INDEX
    Explanations

    references to historical events and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.03
    2:0.07
    3:0.06
    4:0.02
    5:0.07
    6:0.14
    7:0.30
    8:0.06
    9:0.03
    10:0.07
    11:0.08
    Negative Logits
    atum
    -1.54
    Chan
    -1.44
    assi
    -1.43
    tein
    -1.42
    icidal
    -1.40
    onding
    -1.39
    chan
    -1.36
     Cosponsors
    -1.32
    り
    -1.32
    ello
    -1.29
    POSITIVE LOGITS
     prol
    1.25
     Pharaoh
    1.23
     legends
    1.22
     fiction
    1.20
     histor
    1.20
     Archae
    1.18
     Tropical
    1.15
     historians
    1.15
     Glac
    1.15
     folklore
    1.15
    Activations Density 0.059%

    No Known Activations