© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 43991
    Prev
    Next
    INDEX
    Explanations

    comparative expressions and phrases indicating a prioritization of one thing over another

    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
    1:0.01
    2:0.13
    3:0.05
    4:0.14
    5:0.03
    6:0.04
    7:0.29
    8:0.09
    9:0.03
    10:0.04
    11:0.07
    Negative Logits
    redited
    -1.81
    ────────
    -1.76
    RANT
    -1.73
    ────
    -1.64
    iard
    -1.60
    ���
    -1.56
     enthusi
    -1.54
     accredited
    -1.49
    ocry
    -1.48
    ibaba
    -1.47
    POSITIVE LOGITS
     obscurity
    1.76
    die
    1.52
     guarding
    1.50
    eering
    1.49
     Skydragon
    1.47
    Posts
    1.46
    etary
    1.45
    mere
    1.42
     SERV
    1.42
    keeping
    1.41
    Activations Density 0.003%

    No Known Activations