© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 18618
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a need for investigation or clarification regarding a situation or event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    2:0.11
    3:0.07
    4:0.19
    5:0.02
    6:0.02
    7:0.36
    8:0.02
    9:0.03
    10:0.04
    11:0.06
    Negative Logits
    elected
    -1.85
    signed
    -1.74
    keys
    -1.56
    rollers
    -1.55
    abet
    -1.52
    porary
    -1.51
    cells
    -1.50
    thank
    -1.45
    ectomy
    -1.43
    workers
    -1.42
    POSITIVE LOGITS
     discrepancies
    1.96
     inconsistencies
    1.80
     details
    1.80
     inacc
    1.77
     wrongdoing
    1.77
     factual
    1.76
     specifics
    1.74
     weeds
    1.70
     WHY
    1.68
     sourcing
    1.65
    Activations Density 0.000%

    No Known Activations