© 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. 43963
    Prev
    Next
    INDEX
    Explanations

    references to political achievements and their perceived significance

    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
    1:0.01
    2:0.11
    3:0.27
    4:0.11
    5:0.04
    6:0.05
    7:0.06
    8:0.06
    9:0.05
    10:0.08
    11:0.09
    Negative Logits
    ????????
    -1.69
     indo
    -1.66
    )!
    -1.65
    )?
    -1.64
     YOUR
    -1.63
     ;)
    -1.63
     eh
    -1.60
    luaj
    -1.56
     goddamn
    -1.54
    王
    -1.48
    POSITIVE LOGITS
     outright
    1.36
    ailable
    1.35
    excluding
    1.35
     occupancy
    1.33
     overt
    1.31
    atories
    1.29
    verages
    1.28
     excluding
    1.28
    auna
    1.28
    rouch
    1.28
    Activations Density 0.036%

    No Known Activations