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

    Neuronpedia

    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. 7665
    Prev
    Next
    INDEX
    Explanations

    instances of gathering or collection events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    2:0.06
    3:0.05
    4:0.24
    5:0.02
    6:0.04
    7:0.37
    8:0.02
    9:0.03
    10:0.04
    11:0.04
    Negative Logits
    freedom
    -1.69
    omm
    -1.68
    Official
    -1.64
    Clar
    -1.61
    Eat
    -1.56
    enda
    -1.54
     Nig
    -1.53
    ournal
    -1.50
    ioch
    -1.49
    licensed
    -1.49
    POSITIVE LOGITS
     shuffle
    2.15
     adversity
    2.08
     storms
    2.00
     attrition
    1.99
     setbacks
    1.92
     losses
    1.90
     storm
    1.83
     defeats
    1.82
     cynicism
    1.81
     advers
    1.81
    Activations Density 0.000%

    No Known Activations