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. 48
    Prev
    Next
    INDEX
    Explanations

    elements related to significant events or occurrences in history

    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
    1:0.01
    2:0.06
    3:0.47
    4:0.03
    5:0.06
    6:0.02
    7:0.04
    8:0.03
    9:0.01
    10:0.12
    11:0.02
    Negative Logits
     policymakers
    -2.36
     Researchers
    -2.18
     consumers
    -2.09
     taxpayers
    -2.09
     stakeholders
    -2.09
     inspectors
    -2.08
     growers
    -2.08
     Protesters
    -2.03
     shoppers
    -2.00
     motorists
    -2.00
    POSITIVE LOGITS
     charisma
    2.75
     demeanor
    2.67
     stature
    2.63
     persona
    2.55
     passion
    2.55
     obsession
    2.50
     ambitions
    2.44
     aspirations
    2.39
     affiliation
    2.39
     penchant
    2.38
    Activations Density 0.671%

    No Known Activations