© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43917
    Prev
    Next
    INDEX
    Explanations

    references to encyclopedic content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.01
    1:0.01
    2:0.08
    3:0.05
    4:0.04
    5:0.02
    6:0.15
    7:0.28
    8:0.04
    9:0.06
    10:0.17
    11:0.05
    Negative Logits
     veto
    -1.82
     vs
    -1.74
     opposition
    -1.72
     retaliation
    -1.69
     versus
    -1.68
     boo
    -1.66
     retali
    -1.62
    AME
    -1.58
     overpower
    -1.55
     trem
    -1.55
    POSITIVE LOGITS
     mathemat
    2.05
     Journals
    1.94
    cyclopedia
    1.94
     Teaching
    1.90
    externalActionCode
    1.84
    arthed
    1.84
    lished
    1.78
    endium
    1.77
     readable
    1.76
    enment
    1.75
    Activations Density 0.000%

    No Known Activations