© 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. 44641
    Prev
    Next
    INDEX
    Explanations

    references to specific fights and their related events or details

    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
    0:0.03
    1:0.03
    2:0.05
    3:0.06
    4:0.05
    5:0.08
    6:0.03
    7:0.05
    8:0.03
    9:0.07
    10:0.41
    11:0.06
    Negative Logits
     jails
    -1.82
     textbooks
    -1.78
     prisons
    -1.77
     colonies
    -1.74
     Debug
    -1.69
    verbs
    -1.67
     govern
    -1.67
     overcl
    -1.62
     consoles
    -1.62
     governing
    -1.61
    POSITIVE LOGITS
    ..............
    2.14
    GGGGGGGG
    1.90
     surpr
    1.84
    ........................
    1.79
     merits
    1.78
    olicited
    1.77
     ASAP
    1.71
    andem
    1.70
     fian
    1.68
     stopp
    1.68
    Activations Density 0.008%

    No Known Activations