© 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. 7004
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "I mean" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    2:0.06
    3:0.15
    4:0.11
    5:0.02
    6:0.15
    7:0.04
    8:0.03
    9:0.05
    10:0.07
    11:0.24
    Negative Logits
     perpet
    -1.61
    ा
    -1.59
    soType
    -1.54
    imum
    -1.52
     Franchise
    -1.51
     coined
    -1.50
    channelAvailability
    -1.44
    μ
    -1.44
    ="#
    -1.43
    ‎
    -1.42
    POSITIVE LOGITS
     boxes
    1.95
     panels
    1.79
     cages
    1.70
     CONTROL
    1.59
     loads
    1.54
     cryst
    1.52
    levels
    1.49
    ECK
    1.49
    control
    1.46
    hower
    1.46
    Activations Density 0.004%

    No Known Activations