© 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. 5-ATT-KK
    11. 3334
    Prev
    Next
    INDEX
    Explanations

    phrases related to mitigating or reducing negative impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.02
    2:0.05
    3:0.08
    4:0.06
    5:0.03
    6:0.03
    7:0.44
    8:0.04
    9:0.04
    10:0.04
    11:0.10
    Negative Logits
    ourced
    -1.52
    ourcing
    -1.48
     Tuls
    -1.47
    wagon
    -1.47
    IDER
    -1.39
    Posted
    -1.37
    rick
    -1.35
    rawdownloadcloneembedreportprint
    -1.35
    arthed
    -1.34
     Straw
    -1.34
    POSITIVE LOGITS
     overwrite
    1.65
     collapse
    1.53
    essim
    1.52
    erno
    1.48
     catastrophe
    1.47
     ESL
    1.45
     emulation
    1.43
     Survive
    1.43
    Winter
    1.43
     perfection
    1.42
    Activations Density 0.001%

    No Known Activations