© 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. 45608
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly in the context of contact information or affiliations

    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
    0:0.03
    1:0.02
    2:0.09
    3:0.16
    4:0.25
    5:0.04
    6:0.04
    7:0.07
    8:0.05
    9:0.07
    10:0.07
    11:0.06
    Negative Logits
     overwhelmingly
    -1.70
     dwar
    -1.67
     unrecogn
    -1.64
     interrupted
    -1.57
     disproportion
    -1.52
     distinctly
    -1.51
     tract
    -1.50
     assumed
    -1.47
     overt
    -1.46
     overheard
    -1.45
    POSITIVE LOGITS
    ullivan
    1.81
    �
    1.74
    riber
    1.62
    otte
    1.62
    enthal
    1.59
    闘
    1.58
    yip
    1.57
    ibrarian
    1.57
    mbuds
    1.56
    scribe
    1.55
    Activations Density 0.002%

    No Known Activations