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. 1-ATT-KK
    6. 6430
    Prev
    Next
    INDEX
    Explanations

    terms related to financial transactions and company actions such as paying, avoiding, fees, credit, card, plans, donate, proceeds, costs, properties, mortgage, loans, trillion, money, wages, invest, buy, shares, dividends

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.1.attn.hook_z
    Hook Layer
    1
    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
    1:0.06
    2:0.13
    3:0.06
    4:0.08
    5:0.13
    6:0.07
    7:0.04
    8:0.04
    9:0.04
    10:0.12
    11:0.13
    Negative Logits
    amera
    -0.81
    anson
    -0.80
     Murd
    -0.78
    rame
    -0.76
    quickShipAvailable
    -0.76
    ndra
    -0.74
    xual
    -0.72
    akuya
    -0.70
    urion
    -0.70
    undown
    -0.70
    POSITIVE LOGITS
    。
    0.82
    �
    0.79
    */
    0.78
    、
    0.78
    ヘ
    0.77
    ْ
    0.76
    ¯
    0.76
    });
    0.76
    ./
    0.75
     hereafter
    0.73
    Activations Density 0.723%

    No Known Activations