© 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. 43681
    Prev
    Next
    INDEX
    Explanations

    reporting verbs that indicate statements or confirmations

    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
    0:0.04
    1:0.02
    2:0.19
    3:0.05
    4:0.05
    5:0.05
    6:0.04
    7:0.05
    8:0.06
    9:0.05
    10:0.27
    11:0.08
    Negative Logits
     repeal
    -1.69
     Debate
    -1.68
     debates
    -1.66
     treaties
    -1.60
     legisl
    -1.59
     repealing
    -1.59
    Politics
    -1.57
     controversies
    -1.55
    politics
    -1.52
    requ
    -1.52
    POSITIVE LOGITS
    arten
    1.84
     Bagg
    1.84
     alerted
    1.68
    earcher
    1.63
    llah
    1.56
    atis
    1.51
    edi
    1.49
     evacuated
    1.49
     scan
    1.49
     scans
    1.48
    Activations Density 0.001%

    No Known Activations