© 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. 43437
    Prev
    Next
    INDEX
    Explanations

    commas and other punctuation indicating separate clauses or items in a sentence

    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
    2:0.14
    3:0.06
    4:0.07
    5:0.03
    6:0.07
    7:0.17
    8:0.07
    9:0.02
    10:0.12
    11:0.17
    Negative Logits
    ombat
    -1.68
    ��
    -1.60
     Gleaming
    -1.58
    urbed
    -1.55
    culosis
    -1.52
    undown
    -1.50
    itionally
    -1.50
    ibly
    -1.48
    oak
    -1.47
    anwhile
    -1.45
    POSITIVE LOGITS
     Winc
    1.42
     Cumm
    1.39
     collaborator
    1.35
     mates
    1.31
     rivals
    1.30
     publishers
    1.25
    RAW
    1.24
     sibling
    1.24
     param
    1.23
     Grind
    1.22
    Activations Density 0.057%

    No Known Activations