© 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. 46779
    Prev
    Next
    INDEX
    Explanations

    phrases related to requests or appeals for help, especially in legal or distress situations

    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
    2:0.05
    3:0.07
    4:0.10
    5:0.03
    6:0.05
    7:0.36
    8:0.02
    9:0.03
    10:0.13
    11:0.07
    Negative Logits
     Travels
    -1.77
    runtime
    -1.74
     Detected
    -1.46
    paces
    -1.45
    native
    -1.41
     Brune
    -1.40
    clips
    -1.39
     サーティワン
    -1.39
    lived
    -1.39
    bsite
    -1.38
    POSITIVE LOGITS
     plea
    2.18
     plead
    2.02
     pleading
    1.93
     pleas
    1.83
     bluff
    1.75
     repentance
    1.71
     surrender
    1.66
     pled
    1.63
    zzle
    1.63
     pardon
    1.61
    Activations Density 0.006%

    No Known Activations