© 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. 21447
    Prev
    Next
    INDEX
    Explanations

    mentions of specific entities or organizations, particularly in the context of economic or political topics

    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
    0:0.04
    1:0.02
    2:0.17
    3:0.05
    4:0.13
    5:0.10
    6:0.04
    7:0.06
    8:0.08
    9:0.06
    10:0.12
    11:0.07
    Negative Logits
     disadvant
    -1.39
     inconsist
    -1.03
     slippery
    -1.01
     psychiat
    -0.96
     lawy
    -0.96
     juggling
    -0.95
     outing
    -0.94
    romeda
    -0.94
    ikuman
    -0.94
     freeway
    -0.94
    POSITIVE LOGITS
     guid
    1.18
    heed
    1.06
    lycer
    1.04
    Car
    1.02
    ️
    1.02
    ortality
    1.01
     Allow
    1.01
    culosis
    0.98
    Cal
    0.97
    ascus
    0.96
    Activations Density 0.294%

    No Known Activations