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. 10368
    Prev
    Next
    INDEX
    Explanations

    references to private insurance and its relationship with healthcare systems

    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
    0:0.04
    1:0.02
    2:0.08
    3:0.11
    4:0.05
    5:0.04
    6:0.27
    7:0.11
    8:0.04
    9:0.03
    10:0.07
    11:0.09
    Negative Logits
    eway
    -1.19
    owl
    -1.16
    osterone
    -1.14
    ashtra
    -1.07
    oother
    -1.06
    itely
    -1.05
    amera
    -1.04
     WOM
    -1.03
    xual
    -1.02
     Azerbai
    -1.02
    POSITIVE LOGITS
    deals
    1.27
     alike
    1.26
     trusts
    1.24
     dime
    1.22
     commissions
    1.21
     enterprises
    1.20
     foundations
    1.17
     laboratories
    1.16
     initiatives
    1.13
     guarantees
    1.11
    Activations Density 0.024%

    No Known Activations