© 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. 44924
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the seriousness and implications of certain actions or concepts

    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
    2:0.10
    3:0.05
    4:0.09
    5:0.02
    6:0.04
    7:0.47
    8:0.02
    9:0.03
    10:0.05
    11:0.05
    Negative Logits
    dep
    -1.80
    etta
    -1.69
     omission
    -1.65
    locking
    -1.62
    Dep
    -1.56
    arth
    -1.53
     nav
    -1.51
    Enable
    -1.49
    AA
    -1.45
    irit
    -1.45
    POSITIVE LOGITS
     seriously
    1.78
     rightful
    1.68
     overboard
    1.61
     unch
    1.61
     Hispan
    1.60
     stride
    1.59
     Seriously
    1.52
    utterstock
    1.48
     Sinai
    1.46
     Waterloo
    1.45
    Activations Density 0.079%

    No Known Activations