© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 3941
    Prev
    Next
    INDEX
    Explanations

    references to specific types or numbers of items or people

    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
    0:0.13
    1:0.14
    2:0.03
    3:0.03
    4:0.04
    5:0.19
    6:0.03
    7:0.02
    8:0.13
    9:0.07
    10:0.06
    11:0.06
    Negative Logits
    now
    -1.64
    aston
    -1.58
    Page
    -1.58
    shed
    -1.53
    save
    -1.52
    Save
    -1.49
    forth
    -1.47
    have
    -1.43
    Ctrl
    -1.41
    ��極
    -1.39
    POSITIVE LOGITS
     passer
    1.42
     hypothetical
    1.40
     cowork
    1.40
     residential
    1.40
     plasma
    1.32
     Jew
    1.31
     person
    1.29
     hybrid
    1.29
     pickup
    1.27
     coff
    1.27
    Activations Density 0.093%

    No Known Activations