© 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. 2-ATT-KK
    11. 21800
    Prev
    Next
    INDEX
    Explanations

    words related to social and political activism, particularly in terms of demographics and community involvement

    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
    0:0.10
    1:0.01
    2:0.07
    3:0.15
    4:0.04
    5:0.10
    6:0.04
    7:0.06
    8:0.19
    9:0.05
    10:0.10
    11:0.05
    Negative Logits
    quickShipAvailable
    -1.35
    \":
    -1.11
     Rasm
    -1.07
     Salvador
    -1.02
     Romeo
    -1.00
    の�
    -0.99
     Kub
    -0.99
     mustache
    -0.97
    Pad
    -0.97
    �
    -0.96
    POSITIVE LOGITS
    venge
    1.29
    rouse
    1.18
    levels
    1.09
    create
    1.05
    speak
    1.02
     extent
    1.02
    livion
    1.01
    ceive
    1.01
    acceptable
    1.01
    make
    1.00
    Activations Density 0.644%

    No Known Activations