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. 3078
    Prev
    Next
    INDEX
    Explanations

    references to government and financial assistance

    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
    0:0.05
    1:0.43
    2:0.04
    3:0.04
    4:0.04
    5:0.05
    6:0.06
    7:0.05
    8:0.03
    9:0.05
    10:0.05
    11:0.05
    Negative Logits
    multiple
    -2.64
    sometimes
    -2.61
     Ripple
    -2.60
    helps
    -2.57
     Potential
    -2.48
    often
    -2.46
     scams
    -2.45
     Compare
    -2.45
     Reality
    -2.40
     Large
    -2.37
    POSITIVE LOGITS
     shall
    4.97
    shall
    4.71
     SHALL
    4.00
    EngineDebug
    3.97
     hereby
    3.83
     hereafter
    3.82
     afore
    3.71
    ◼
    3.64
     thereto
    3.60
     requisite
    3.55
    Activations Density 0.010%

    No Known Activations