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. 3123
    Prev
    Next
    INDEX
    Explanations

    terms related to higher education funding and policy changes

    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
    0:0.30
    1:0.02
    2:0.14
    3:0.12
    4:0.03
    5:0.12
    6:0.03
    7:0.08
    8:0.05
    9:0.02
    10:0.03
    11:0.02
    Negative Logits
     MOT
    -2.10
    Motor
    -2.08
     Chevrolet
    -2.04
     Garmin
    -2.03
     Motor
    -2.02
     droid
    -2.01
     fisherman
    -2.00
     headlights
    -1.99
    wheel
    -1.97
    Pink
    -1.95
    POSITIVE LOGITS
     tuition
    3.91
     campuses
    3.89
     scholarships
    3.15
     curric
    3.11
     Universities
    3.07
     universities
    3.05
    iversity
    3.01
     campus
    2.99
     faculty
    2.96
     alumni
    2.94
    Activations Density 0.140%

    No Known Activations