© 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. 43543
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a listing or enumeration of items or examples

    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
    0:0.01
    1:0.01
    2:0.13
    3:0.18
    4:0.10
    5:0.03
    6:0.08
    7:0.09
    8:0.06
    9:0.03
    10:0.07
    11:0.16
    Negative Logits
    ��極
    -1.76
    ��
    -1.65
    EStream
    -1.60
    ��
    -1.56
    龍喚士
    -1.43
    士
    -1.40
    ghazi
    -1.38
    iano
    -1.28
    bah
    -1.26
     神
    -1.24
    POSITIVE LOGITS
    etsy
    1.27
     unanswered
    1.17
     flourishing
    1.15
    coming
    1.13
     swirling
    1.13
     buzzing
    1.12
     popping
    1.12
     happening
    1.11
     unheard
    1.10
     unwanted
    1.07
    Activations Density 0.039%

    No Known Activations