© 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. 41829
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and specific symbols indicating emphasis or separations in text

    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
    0:0.02
    1:0.04
    2:0.21
    3:0.20
    4:0.09
    5:0.04
    6:0.04
    7:0.10
    8:0.05
    9:0.04
    10:0.07
    11:0.04
    Negative Logits
     periodically
    -1.55
     awake
    -1.50
     resume
    -1.41
    !'"
    -1.31
    iatus
    -1.29
     unfinished
    -1.28
     resumes
    -1.27
    Repeat
    -1.27
     refreshed
    -1.27
     Tribunal
    -1.25
    POSITIVE LOGITS
    qqa
    1.79
    kit
    1.58
    issance
    1.52
    088
    1.49
    ガ
    1.48
     MILL
    1.45
    �
    1.44
    "]=>
    1.42
    bidden
    1.39
    aga
    1.37
    Activations Density 0.000%

    No Known Activations