© 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. 42329
    Prev
    Next
    INDEX
    Explanations

    references to specific people, organizations, and significant entities

    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
    2:0.11
    3:0.09
    4:0.34
    5:0.03
    6:0.04
    7:0.05
    8:0.03
    9:0.04
    10:0.09
    11:0.07
    Negative Logits
     Fathers
    -1.59
     Gods
    -1.47
     pneum
    -1.45
     Proced
    -1.43
     Helm
    -1.42
     clich
    -1.40
     MH
    -1.36
     physic
    -1.34
     '.
    -1.33
     customary
    -1.32
    POSITIVE LOGITS
     pione
    1.64
     subur
    1.64
    quartered
    1.60
    oreAnd
    1.54
    ounded
    1.54
    DeliveryDate
    1.47
    
    1.39
    cum
    1.38
    
    1.37
    �
    1.37
    Activations Density 0.013%

    No Known Activations