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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10011
    Prev
    Next
    INDEX
    Explanations

    expressions related to borrowing, finance, and monetary transactions

    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
    0:0.02
    1:0.02
    2:0.10
    3:0.08
    4:0.02
    5:0.04
    6:0.04
    7:0.09
    8:0.08
    9:0.30
    10:0.06
    11:0.10
    Negative Logits
     disappearance
    -1.25
    rican
    -1.23
    chrom
    -1.17
    ople
    -1.15
    amiya
    -1.12
    ixel
    -1.10
    orest
    -1.10
    ika
    -1.10
     fracture
    -1.07
     visible
    -1.06
    POSITIVE LOGITS
    ilk
    1.45
    sein
    1.40
     srfAttach
    1.25
     cheaply
    1.19
     constitu
    1.17
     analogy
    1.11
     coh
    1.06
     Milton
    1.05
    kefeller
    1.05
    })
    1.04
    Activations Density 0.011%

    No Known Activations