© 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. 28301
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the "first phase" of projects or inquiries

    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
    0:0.03
    1:0.03
    2:0.12
    3:0.06
    4:0.09
    5:0.04
    6:0.07
    7:0.30
    8:0.04
    9:0.04
    10:0.07
    11:0.06
    Negative Logits
    agascar
    -1.89
    gmail
    -1.76
    nces
    -1.73
    龍契士
    -1.72
    iguous
    -1.71
    ciating
    -1.67
    osponsors
    -1.54
    quished
    -1.52
    miah
    -1.52
     humiliated
    -1.49
    POSITIVE LOGITS
     renovation
    1.78
     takeover
    1.73
     inquiry
    1.64
     project
    1.62
     transformation
    1.61
     restructuring
    1.55
     resh
    1.55
     revolution
    1.54
     proposal
    1.53
     revital
    1.51
    Activations Density 0.001%

    No Known Activations