© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 5756
    Prev
    Next
    INDEX
    Explanations

    instances of negation and expressions of exception

    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
    1:0.05
    2:0.05
    3:0.02
    4:0.02
    5:0.37
    6:0.03
    7:0.04
    8:0.05
    9:0.06
    10:0.12
    11:0.11
    Negative Logits
     Greenwich
    -1.59
    door
    -1.59
    ARGET
    -1.54
     2050
    -1.51
     respectively
    -1.44
     sidx
    -1.42
    iants
    -1.40
    cellaneous
    -1.39
    vik
    -1.37
    itatively
    -1.37
    POSITIVE LOGITS
     nor
    3.18
     anymore
    2.93
     Flavoring
    2.18
    nor
    2.14
     :(
    2.13
     unless
    2.01
    yet
    1.98
    ��
    1.91
     anyways
    1.83
    unless
    1.81
    Activations Density 1.113%

    No Known Activations