© 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. 44881
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causality or relationships between different elements

    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
    0:0.03
    1:0.01
    2:0.08
    3:0.08
    4:0.17
    5:0.02
    6:0.03
    7:0.29
    8:0.02
    9:0.03
    10:0.09
    11:0.09
    Negative Logits
     goodbye
    -1.64
    ariat
    -1.63
    imilation
    -1.59
    itone
    -1.42
    boro
    -1.42
    anooga
    -1.37
    respect
    -1.36
    ulum
    -1.35
     Goodbye
    -1.34
    olesterol
    -1.32
    POSITIVE LOGITS
     disturbances
    1.56
     discrepancies
    1.56
     derive
    1.55
     arise
    1.54
     arising
    1.51
     arises
    1.45
     Mysteries
    1.44
     formations
    1.42
     revolutions
    1.41
     differently
    1.39
    Activations Density 0.002%

    No Known Activations