© 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. 1881
    Prev
    Next
    INDEX
    Explanations

    references to difficulty in finding or accessing something

    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
    0:0.03
    1:0.03
    2:0.07
    3:0.06
    4:0.16
    5:0.06
    6:0.05
    7:0.23
    8:0.05
    9:0.06
    10:0.07
    11:0.06
    Negative Logits
     impunity
    -1.76
     asymm
    -1.66
     climate
    -1.59
     contingency
    -1.59
     premature
    -1.58
     quake
    -1.57
     alienation
    -1.55
     meltdown
    -1.53
     independence
    -1.53
     irreversible
    -1.52
    POSITIVE LOGITS
    bilt
    1.82
    liga
    1.74
    Magazine
    1.73
    osponsors
    1.72
    arag
    1.62
    hl
    1.59
    ilk
    1.56
     kitchens
    1.55
    uti
    1.51
    ertation
    1.49
    Activations Density 0.000%

    No Known Activations