© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 11486
    Prev
    Next
    INDEX
    Explanations

    phrases expressing intention or desire

    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
    2:0.07
    3:0.03
    4:0.02
    5:0.02
    6:0.10
    7:0.07
    8:0.06
    9:0.25
    10:0.04
    11:0.22
    Negative Logits
    NBA
    -1.36
    carry
    -1.24
     otherwise
    -1.19
     nevertheless
    -1.16
     Participation
    -1.05
     formerly
    -1.04
    spir
    -1.03
    Enough
    -1.03
    SUP
    -1.01
    Vol
    -0.99
    POSITIVE LOGITS
    natureconservancy
    1.40
    ��
    1.29
    :]
    1.25
    tions
    1.23
    opsy
    1.22
    enza
    1.20
    ��
    1.16
    thodox
    1.16
    ysis
    1.16
    isite
    1.14
    Activations Density 0.016%

    No Known Activations