© 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. 22981
    Prev
    Next
    INDEX
    Explanations

    destructive or unfavorable situations or actions, such as government inefficiency, violence, or controversial decisions

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

    references to "those" leading to particular categories or descriptors

    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
    0:0.07
    1:0.03
    2:0.06
    3:0.15
    4:0.05
    5:0.07
    6:0.06
    7:0.11
    8:0.04
    9:0.08
    10:0.15
    11:0.08
    Negative Logits
    ���
    -0.83
    enegger
    -0.81
     Alley
    -0.76
     cx
    -0.76
    atre
    -0.76
    uthor
    -0.75
    dylib
    -0.72
     Que
    -0.70
    ruary
    -0.70
    availability
    -0.69
    POSITIVE LOGITS
    natureconservancy
    1.04
    azeera
    0.87
    uyomi
    0.87
    pez
    0.86
     defy
    0.84
    cemic
    0.84
     empires
    0.81
     survived
    0.81
    oran
    0.81
     defied
    0.80
    Activations Density 0.047%

    No Known Activations