© 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. 42244
    Prev
    Next
    INDEX
    Explanations

    administrative actions and processes related to governance and schedules

    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
    0:0.06
    1:0.17
    2:0.05
    3:0.06
    4:0.04
    5:0.19
    6:0.05
    7:0.04
    8:0.07
    9:0.08
    10:0.08
    11:0.05
    Negative Logits
    lux
    -1.42
     batted
    -1.35
     stranded
    -1.34
     Joy
    -1.33
    cious
    -1.32
    zek
    -1.29
     Wolver
    -1.29
    umatic
    -1.26
    que
    -1.26
    Queen
    -1.25
    POSITIVE LOGITS
     Achievements
    1.46
    location
    1.42
    ername
    1.42
    Particip
    1.36
    particip
    1.36
    ander
    1.33
    settings
    1.31
    �
    1.31
    elist
    1.31
     Practices
    1.30
    Activations Density 0.000%

    No Known Activations