© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 7228
    Prev
    Next
    INDEX
    Explanations

    verbs and their forms, particularly in relation to actions and conditions

    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
    1:0.06
    2:0.13
    3:0.04
    4:0.02
    5:0.04
    6:0.07
    7:0.05
    8:0.12
    9:0.16
    10:0.10
    11:0.14
    Negative Logits
    onomy
    -0.99
    Motion
    -0.98
    cosystem
    -0.95
     acronym
    -0.90
    Merc
    -0.90
    cean
    -0.89
    ety
    -0.87
    ��
    -0.87
    Discussion
    -0.87
     misconception
    -0.85
    POSITIVE LOGITS
     anymore
    2.22
     nor
    1.48
     anytime
    1.26
    unless
    1.23
     any
    1.23
     anything
    1.22
     tomorrow
    1.15
     unless
    1.14
     ANY
    1.10
     until
    1.10
    Activations Density 0.023%

    No Known Activations