Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 8434
    Prev
    Next
    INDEX
    Explanations

    terms related to investment funds and financial instruments

    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
    0:0.33
    1:0.04
    2:0.04
    3:0.06
    4:0.07
    5:0.05
    6:0.06
    7:0.08
    8:0.05
    9:0.04
    10:0.09
    11:0.04
    Negative Logits
    �
    -1.71
    VIDIA
    -1.54
    alus
    -1.50
     blot
    -1.39
     rain
    -1.38
     scen
    -1.37
     floppy
    -1.35
     hello
    -1.35
     ray
    -1.34
     rapp
    -1.34
    POSITIVE LOGITS
    vice
    1.64
    Maker
    1.61
    enum
    1.50
    Corp
    1.50
    sense
    1.47
    artments
    1.47
     portfolio
    1.45
    essor
    1.45
    wright
    1.40
    holder
    1.38
    Activations Density 0.003%

    No Known Activations