© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 7955
    Prev
    Next
    INDEX
    Explanations

    key terms related to economics and policy issues

    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
    1:0.10
    2:0.26
    3:0.02
    4:0.02
    5:0.06
    6:0.09
    7:0.05
    8:0.09
    9:0.08
    10:0.07
    11:0.09
    Negative Logits
    usercontent
    -1.45
    NetMessage
    -1.30
    mails
    -1.20
    ernels
    -1.19
    sites
    -1.13
    prints
    -1.09
     equivalents
    -1.08
     chromosomes
    -1.08
     heirs
    -1.08
    aters
    -1.08
    POSITIVE LOGITS
     standpoint
    1.55
     perspective
    1.39
    otomy
    1.23
    inar
    1.18
     twist
    1.14
     consisting
    1.12
     vantage
    1.11
     session
    1.10
     background
    1.10
     example
    1.09
    Activations Density 0.188%

    No Known Activations