© 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. 27927
    Prev
    Next
    INDEX
    Explanations

    references to prominent organizations, entities, and events

    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
    0:0.10
    1:0.21
    2:0.04
    3:0.04
    4:0.04
    5:0.23
    6:0.03
    7:0.02
    8:0.07
    9:0.06
    10:0.05
    11:0.05
    Negative Logits
    lement
    -2.13
    alle
    -1.90
    ーティ
    -1.83
    ances
    -1.82
    omething
    -1.80
    ily
    -1.79
    andra
    -1.78
    lem
    -1.78
    atson
    -1.76
    alam
    -1.76
    POSITIVE LOGITS
    PRES
    2.16
     publishes
    2.05
     inaug
    1.99
     Publishing
    1.90
     PRESS
    1.89
     Presents
    1.89
     coined
    1.88
     Masquerade
    1.83
     organising
    1.77
     Pub
    1.77
    Activations Density 0.003%

    No Known Activations