© 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. 43649
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and operations

    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
    2:0.43
    3:0.10
    4:0.07
    5:0.02
    6:0.07
    7:0.03
    8:0.05
    9:0.04
    10:0.04
    11:0.04
    Negative Logits
     coats
    -1.20
     timestamp
    -1.19
     Nek
    -1.14
     Lowry
    -1.12
     cutoff
    -1.11
     filibuster
    -1.10
     noun
    -1.10
    identally
    -1.09
     assessed
    -1.08
    odynamic
    -1.07
    POSITIVE LOGITS
    MpServer
    1.86
    externalActionCode
    1.70
    umbn
    1.68
    Interstitial
    1.64
    advertisement
    1.50
    bes
    1.50
     Lauder
    1.46
    berus
    1.39
    cest
    1.35
    vil
    1.31
    Activations Density 0.080%

    No Known Activations