© 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. 40788
    Prev
    Next
    INDEX
    Explanations

    references to individuals, particularly in religious or historical contexts

    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
    0:0.04
    1:0.04
    2:0.08
    3:0.07
    4:0.33
    5:0.05
    6:0.08
    7:0.04
    8:0.06
    9:0.03
    10:0.07
    11:0.05
    Negative Logits
    VERTISEMENT
    -1.55
     fits
    -1.54
     seamlessly
    -1.47
     tack
    -1.47
     ****
    -1.43
     digitally
    -1.39
     favorably
    -1.38
     stress
    -1.36
     waivers
    -1.36
     airs
    -1.35
    POSITIVE LOGITS
    eworld
    1.71
    udence
    1.64
     ancestors
    1.63
    masters
    1.54
    Engineers
    1.54
    uckland
    1.53
    rius
    1.52
    アル
    1.52
     GOD
    1.44
    rolet
    1.41
    Activations Density 0.004%

    No Known Activations