© 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. 40031
    Prev
    Next
    INDEX
    Explanations

    sentences related to government actions or documents, particularly around topics of oversight or reporting

    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
    0:0.12
    1:0.03
    2:0.10
    3:0.09
    4:0.05
    5:0.06
    6:0.02
    7:0.03
    8:0.28
    9:0.07
    10:0.05
    11:0.05
    Negative Logits
    seys
    -1.55
    ypes
    -1.52
    osponsors
    -1.50
    racuse
    -1.49
    yrus
    -1.47
    zan
    -1.46
    conservancy
    -1.46
    hedon
    -1.45
    trak
    -1.41
    asts
    -1.38
    POSITIVE LOGITS
    )=(
    2.02
     Anyway
    1.79
    actionDate
    1.51
     ALSO
    1.46
     Another
    1.46
     minus
    1.46
     Versus
    1.45
     Secondly
    1.40
    redit
    1.38
    �
    1.36
    Activations Density 0.054%

    No Known Activations