© 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. 39951
    Prev
    Next
    INDEX
    Explanations

    references to directors or leadership roles in various organizations

    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
    0:0.02
    1:0.02
    2:0.05
    3:0.06
    4:0.09
    5:0.01
    6:0.09
    7:0.37
    8:0.02
    9:0.03
    10:0.08
    11:0.12
    Negative Logits
    龍
    -1.78
    ancy
    -1.46
     Zup
    -1.44
    terday
    -1.43
    Sov
    -1.40
     excuse
    -1.39
     pretext
    -1.39
     subsequ
    -1.32
    �
    -1.32
     tales
    -1.32
    POSITIVE LOGITS
    irit
    1.46
     Cellular
    1.43
    sych
    1.42
    ilic
    1.41
    iral
    1.40
     Sloan
    1.39
    alore
    1.36
     sul
    1.35
     distribut
    1.33
     STD
    1.33
    Activations Density 0.021%

    No Known Activations