© 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. 7588
    Prev
    Next
    INDEX
    Explanations

    phrases related to difficulty and struggle, particularly in challenging situations

    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
    0:0.01
    1:0.02
    2:0.07
    3:0.07
    4:0.01
    5:0.03
    6:0.06
    7:0.33
    8:0.09
    9:0.03
    10:0.06
    11:0.17
    Negative Logits
    folios
    -1.34
    auri
    -1.26
    untled
    -1.17
    orks
    -1.13
    eon
    -1.09
    abo
    -1.07
    OUP
    -1.07
     Gleaming
    -1.05
    elligent
    -1.03
    vous
    -1.01
    POSITIVE LOGITS
     CTR
    1.26
     DK
    1.11
    DCS
    1.09
    ファ
    1.01
     Nanto
    1.01
     NCT
    0.99
    FML
    0.98
     DF
    0.96
     achieving
    0.94
     RL
    0.93
    Activations Density 0.042%

    No Known Activations