© 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. 27776
    Prev
    Next
    INDEX
    Explanations

    references to potential political involvement and candidacies

    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
    0:0.01
    1:0.01
    2:0.17
    3:0.13
    4:0.12
    5:0.03
    6:0.02
    7:0.07
    8:0.06
    9:0.06
    10:0.17
    11:0.09
    Negative Logits
    PLIED
    -1.44
    tyard
    -1.32
     helpless
    -1.30
    acter
    -1.27
    erial
    -1.25
    ��
    -1.17
     admon
    -1.15
     Passive
    -1.15
     abhor
    -1.11
     countless
    -1.09
    POSITIVE LOGITS
     someday
    2.08
     tomorrow
    1.75
    soDeliveryDate
    1.73
     ASAP
    1.69
    morrow
    1.65
     2019
    1.55
     plans
    1.54
     Tomorrow
    1.48
     forthcoming
    1.48
    possibly
    1.47
    Activations Density 0.636%

    No Known Activations