© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 20077
    Prev
    Next
    INDEX
    Explanations

    references to statistical data or historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.02
    2:0.04
    3:0.26
    4:0.02
    5:0.06
    6:0.01
    7:0.09
    8:0.02
    9:0.01
    10:0.36
    11:0.02
    Negative Logits
     tomorrow
    -3.27
     upcoming
    -2.91
     2018
    -2.68
     tonight
    -2.67
     forthcoming
    -2.50
     next
    -2.45
    morrow
    -2.45
    next
    -2.43
     recent
    -2.34
     Recent
    -2.33
    POSITIVE LOGITS
     consisted
    3.04
     tended
    2.87
     existed
    2.79
     depended
    2.67
     lacked
    2.64
     boasted
    2.60
     seemed
    2.58
     relied
    2.56
     assumed
    2.46
     ranged
    2.46
    Activations Density 0.567%

    No Known Activations