© 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. 43567
    Prev
    Next
    INDEX
    Explanations

    phrases related to explanations or clarity of concepts and actions

    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
    1:0.02
    2:0.05
    3:0.08
    4:0.10
    5:0.02
    6:0.04
    7:0.45
    8:0.02
    9:0.02
    10:0.07
    11:0.06
    Negative Logits
    elight
    -2.08
    ヘ
    -1.73
    emouth
    -1.62
    erity
    -1.62
    mouth
    -1.54
    cedented
    -1.50
    ibaba
    -1.50
     pilgr
    -1.44
    ngth
    -1.43
    rive
    -1.41
    POSITIVE LOGITS
    why
    2.09
     WHY
    2.08
     why
    2.07
     aloud
    1.93
     gist
    1.90
    actionDate
    1.84
     intric
    1.81
     convoluted
    1.81
     complicated
    1.79
     misunderstand
    1.79
    Activations Density 0.054%

    No Known Activations