© 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. 41105
    Prev
    Next
    INDEX
    Explanations

    references to discussions or conversations, particularly in relation to important topics or 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
    1:0.01
    2:0.15
    3:0.07
    4:0.12
    5:0.03
    6:0.03
    7:0.24
    8:0.03
    9:0.03
    10:0.12
    11:0.10
    Negative Logits
    adra
    -1.42
    advertising
    -1.40
    float
    -1.32
     commenter
    -1.31
    ム
    -1.26
    oyal
    -1.25
     contiguous
    -1.18
    ンジ
    -1.17
     {:
    -1.14
    brates
    -1.13
    POSITIVE LOGITS
     firsthand
    1.54
    rompt
    1.50
     nep
    1.44
     specifics
    1.44
     mediation
    1.43
     urgent
    1.39
     directions
    1.38
    Prep
    1.35
    erness
    1.34
     aloud
    1.32
    Activations Density 0.012%

    No Known Activations