© 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. 2-ATT-KK
    11. 22996
    Prev
    Next
    INDEX
    Explanations

    expressions of sympathy for various situations

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

    instances of sympathy towards individuals or groups in various contexts

    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
    0:0.05
    1:0.03
    2:0.10
    3:0.04
    4:0.27
    5:0.06
    6:0.03
    7:0.03
    8:0.07
    9:0.18
    10:0.05
    11:0.03
    Negative Logits
     fixtures
    -1.35
    umbers
    -1.32
    ocument
    -1.30
    ipment
    -1.27
    razil
    -1.25
    announced
    -1.23
     refurb
    -1.21
    ivari
    -1.19
    bang
    -1.19
     nap
    -1.17
    POSITIVE LOGITS
     bigotry
    1.34
     Lesbian
    1.30
     Religious
    1.28
    WB
    1.26
     Abortion
    1.24
    TEXTURE
    1.22
     sentiments
    1.22
     colleg
    1.22
     sympathetic
    1.19
     plight
    1.18
    Activations Density 0.003%

    No Known Activations