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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 13661
    Prev
    Next
    INDEX
    Explanations

    numbers related to monetary values

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    0:0.08
    1:0.02
    2:0.10
    3:0.15
    4:0.06
    5:0.13
    6:0.03
    7:0.02
    8:0.08
    9:0.17
    10:0.07
    11:0.04
    Negative Logits
     Anarchy
    -1.12
    erman
    -1.09
    Wiki
    -1.09
    aign
    -1.09
    eda
    -1.08
    Creat
    -1.07
     Franz
    -1.05
     Grac
    -1.05
     Vulcan
    -1.04
    Scotland
    -1.02
    POSITIVE LOGITS
     duplication
    1.07
     deductible
    1.04
    olphins
    1.03
     Reserved
    1.01
     losses
    1.00
     spilled
    1.00
     spills
    0.99
     conceivable
    0.98
     relates
    0.98
     ref
    0.97
    Activations Density 0.059%

    No Known Activations