© 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. 5-ATT-KK
    6. 42737
    Prev
    Next
    INDEX
    Explanations

    instances of the word "improve" and its variations in relation to economic, social, and personal development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.05
    3:0.07
    4:0.16
    5:0.02
    6:0.04
    7:0.39
    8:0.03
    9:0.03
    10:0.06
    11:0.06
    Negative Logits
    netflix
    -1.33
     Straw
    -1.32
     externalToEVAOnly
    -1.30
    imei
    -1.30
     Antarctica
    -1.26
     beck
    -1.25
     Voyager
    -1.24
     Fenrir
    -1.24
     commercials
    -1.23
     arrog
    -1.22
    POSITIVE LOGITS
     responsiveness
    1.90
     improved
    1.84
    Improve
    1.66
     competitiveness
    1.66
     improve
    1.65
     productivity
    1.63
     Improve
    1.61
     Improved
    1.60
     efficiency
    1.57
     improving
    1.56
    Activations Density 0.064%

    No Known Activations