© 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. 43824
    Prev
    Next
    INDEX
    Explanations

    numerical data indicating statistics or rankings

    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
    0:0.17
    1:0.05
    2:0.11
    3:0.07
    4:0.05
    5:0.05
    6:0.12
    7:0.02
    8:0.11
    9:0.07
    10:0.05
    11:0.07
    Negative Logits
    ™:
    -2.15
    DAQ
    -2.05
    ット
    -2.04
    ˈ
    -1.96
    ®
    -1.86
    ーク
    -1.86
     ®
    -1.82
    76561
    -1.77
    �
    -1.72
    ██
    -1.66
    POSITIVE LOGITS
    inent
    1.71
     smokes
    1.63
     versa
    1.61
    idi
    1.56
    ench
    1.51
    hoe
    1.48
    undy
    1.48
    ohan
    1.47
    ewater
    1.45
    enser
    1.43
    Activations Density 0.000%

    No Known Activations