© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 43811
    Prev
    Next
    INDEX
    Explanations

    phrases that convey summaries or conclusions

    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
    1:0.01
    2:0.12
    3:0.09
    4:0.11
    5:0.03
    6:0.04
    7:0.27
    8:0.03
    9:0.04
    10:0.08
    11:0.10
    Negative Logits
    jab
    -1.68
    emies
    -1.54
    ariat
    -1.52
    iaz
    -1.48
    thouse
    -1.47
    cest
    -1.46
    rex
    -1.44
    culosis
    -1.38
    stadt
    -1.37
    urn
    -1.37
    POSITIVE LOGITS
     exquisite
    1.34
     simple
    1.33
     loosely
    1.28
     differently
    1.23
     circumst
    1.23
     purely
    1.21
     impe
    1.21
     neatly
    1.21
     unamb
    1.20
     beautifully
    1.20
    Activations Density 0.011%

    No Known Activations