© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 5468
    Prev
    Next
    INDEX
    Explanations

    repeated sequences of characters or phonemes, particularly those related to the name "Ro.zz" and its variations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.04
    1:0.03
    2:0.08
    3:0.31
    4:0.02
    5:0.02
    6:0.11
    7:0.07
    8:0.05
    9:0.06
    10:0.07
    11:0.08
    Negative Logits
    catentry
    -1.43
     srfAttach
    -1.38
    displayText
    -1.25
    Spoiler
    -1.20
    gage
    -1.15
    channelAvailability
    -1.11
     safegu
    -1.09
    leness
    -1.06
    rehens
    -1.05
    quickShipAvailable
    -1.04
    POSITIVE LOGITS
    acea
    1.41
     Rampage
    1.26
    kefeller
    1.24
    velt
    1.22
    cki
    1.18
    owicz
    1.17
     Janeiro
    1.15
    heid
    1.15
    bilt
    1.15
    nels
    1.13
    Activations Density 0.008%

    No Known Activations