© 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. 3119
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers in a specific format, likely referencing dates or scores

    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
    0:0.19
    1:0.16
    2:0.03
    3:0.03
    4:0.02
    5:0.19
    6:0.05
    7:0.02
    8:0.08
    9:0.10
    10:0.05
    11:0.03
    Negative Logits
    brance
    -1.35
    */(
    -1.30
     TAG
    -1.29
     straw
    -1.27
     triglycer
    -1.26
     pellets
    -1.26
     CAM
    -1.25
     CLA
    -1.20
    =-=-=-=-=-=-=-=-
    -1.20
    mia
    -1.19
    POSITIVE LOGITS
    ��
    1.97
    18
    1.85
    08
    1.77
    17
    1.76
    16
    1.75
    20
    1.70
    09
    1.67
    23
    1.66
    05
    1.65
    �
    1.64
    Activations Density 0.007%

    No Known Activations