© 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. 36960
    Prev
    Next
    INDEX
    Explanations

    phrases involving exaggeration or things being blown out of proportion

    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
    2:0.17
    3:0.07
    4:0.09
    5:0.04
    6:0.13
    7:0.19
    8:0.04
    9:0.04
    10:0.06
    11:0.06
    Negative Logits
    soDeliveryDate
    -1.61
    antz
    -1.56
    ostic
    -1.54
    sit
    -1.53
    orers
    -1.51
    cens
    -1.51
    oplan
    -1.48
    advertisement
    -1.45
    ua
    -1.41
    iquette
    -1.39
    POSITIVE LOGITS
     frenzy
    1.50
     spotlight
    1.44
     catapult
    1.43
     inciner
    1.42
    ado
    1.40
     Gilmore
    1.40
    Charges
    1.31
     proport
    1.31
     shattering
    1.31
     Berserker
    1.31
    Activations Density 0.001%

    No Known Activations