© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 10704
    Prev
    Next
    INDEX
    Explanations

    references to human needs and societal 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
    1:0.06
    2:0.16
    3:0.02
    4:0.02
    5:0.07
    6:0.13
    7:0.07
    8:0.05
    9:0.04
    10:0.05
    11:0.23
    Negative Logits
     classmate
    -1.50
     Sweeney
    -1.38
     teammate
    -1.37
     Hanson
    -1.34
     Scorp
    -1.34
    bull
    -1.32
     Irving
    -1.28
     backdrop
    -1.27
     Chair
    -1.26
     laureate
    -1.25
    POSITIVE LOGITS
    pees
    1.81
     therap
    1.59
     seiz
    1.55
     condem
    1.54
    Sov
    1.52
    inished
    1.50
    WAYS
    1.40
     perished
    1.39
     answ
    1.38
    insured
    1.34
    Activations Density 0.011%

    No Known Activations