© 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. 45043
    Prev
    Next
    INDEX
    Explanations

    references to health care policies and taxation

    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
    1:0.02
    2:0.08
    3:0.08
    4:0.26
    5:0.04
    6:0.04
    7:0.16
    8:0.04
    9:0.04
    10:0.08
    11:0.06
    Negative Logits
    ��
    -2.09
    vation
    -1.72
    addin
    -1.66
     Pavilion
    -1.63
     coron
    -1.59
    utor
    -1.54
    ouch
    -1.53
    pta
    -1.52
    ovember
    -1.50
    ono
    -1.48
    POSITIVE LOGITS
     accordingly
    2.23
     appropri
    1.77
     differently
    1.64
     NAD
    1.53
     disg
    1.48
    Ingredients
    1.48
    rogens
    1.36
     Logged
    1.35
     objectively
    1.34
     offending
    1.33
    Activations Density 0.000%

    No Known Activations