© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22923
    Prev
    Next
    INDEX
    Explanations

    phrases related to workplace, job roles, and professional skills

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to workplace analytics and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.03
    2:0.25
    3:0.11
    4:0.13
    5:0.05
    6:0.03
    7:0.02
    8:0.09
    9:0.12
    10:0.06
    11:0.03
    Negative Logits
    ucc
    -1.58
    ieg
    -1.47
    dot
    -1.43
    othy
    -1.41
    itu
    -1.38
     nep
    -1.33
    inventoryQuantity
    -1.29
    iscal
    -1.29
    uga
    -1.28
    otide
    -1.28
    POSITIVE LOGITS
     Manual
    1.50
     Warehouse
    1.49
     Directory
    1.33
     GOODMAN
    1.29
     Prevention
    1.28
     Equality
    1.27
     Baton
    1.25
     Accountability
    1.22
    Keefe
    1.22
     SQ
    1.22
    Activations Density 0.006%

    No Known Activations