© 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. 43664
    Prev
    Next
    INDEX
    Explanations

    pronouns and specific references to individuals

    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
    1:0.02
    2:0.03
    3:0.05
    4:0.04
    5:0.04
    6:0.47
    7:0.05
    8:0.04
    9:0.06
    10:0.06
    11:0.08
    Negative Logits
    hower
    -1.34
    shire
    -1.33
     pulp
    -1.29
    ATTLE
    -1.15
    advertisement
    -1.13
    MJ
    -1.12
     Violet
    -1.11
    reviewed
    -1.10
     gates
    -1.06
    GREEN
    -1.05
    POSITIVE LOGITS
    EStream
    1.49
    agog
    1.47
    opian
    1.42
    ensitive
    1.37
    ukong
    1.36
    idi
    1.36
    xual
    1.36
    amia
    1.35
    uddin
    1.34
    ovi
    1.30
    Activations Density 0.001%

    No Known Activations