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. 10679
    Prev
    Next
    INDEX
    Explanations

    aspects related to real estate development and funding activities

    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
    1:0.03
    2:0.14
    3:0.09
    4:0.03
    5:0.07
    6:0.03
    7:0.07
    8:0.07
    9:0.03
    10:0.06
    11:0.02
    Negative Logits
    journal
    -2.78
     journals
    -2.64
     instructors
    -2.52
     RIP
    -2.47
     LT
    -2.45
    CTV
    -2.44
     Journals
    -2.44
     subscriptions
    -2.44
     archive
    -2.41
     archived
    -2.41
    POSITIVE LOGITS
     redevelop
    3.57
     tile
    3.23
     redevelopment
    3.21
     zoning
    3.20
     HUD
    3.19
    HUD
    3.17
    estate
    3.10
     developer
    3.08
    perties
    2.94
    tile
    2.90
    Activations Density 0.017%

    No Known Activations