© 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. 43378
    Prev
    Next
    INDEX
    Explanations

    phrases indicating desperation or strong desires

    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
    2:0.07
    3:0.06
    4:0.08
    5:0.03
    6:0.06
    7:0.33
    8:0.03
    9:0.04
    10:0.10
    11:0.10
    Negative Logits
    20439
    -1.44
    actionDate
    -1.36
    stellar
    -1.31
    zynski
    -1.28
     Lerner
    -1.27
    Sing
    -1.26
     lectures
    -1.25
     Participant
    -1.25
    asonic
    -1.23
     Declaration
    -1.22
    POSITIVE LOGITS
     revenge
    1.80
    venge
    1.58
     reconnect
    1.54
     evict
    1.52
     stuffing
    1.51
     escaping
    1.46
     retribution
    1.45
     vengeance
    1.45
    rill
    1.43
     recover
    1.40
    Activations Density 0.004%

    No Known Activations