© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43167
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a replacement or alternative

    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
    1:0.03
    2:0.09
    3:0.05
    4:0.16
    5:0.04
    6:0.02
    7:0.32
    8:0.04
    9:0.03
    10:0.05
    11:0.10
    Negative Logits
     adolesc
    -1.45
     advoc
    -1.39
    �
    -1.34
    Percent
    -1.34
     resil
    -1.31
     Janeiro
    -1.29
    ession
    -1.28
     Commit
    -1.27
    itals
    -1.25
     commits
    -1.25
    POSITIVE LOGITS
    agher
    1.29
    forts
    1.24
    anza
    1.21
     clutter
    1.21
    awed
    1.19
    adle
    1.19
    tur
    1.17
     Bloom
    1.17
     Cellular
    1.17
     Kush
    1.16
    Activations Density 0.003%

    No Known Activations