© 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. 44576
    Prev
    Next
    INDEX
    Explanations

    references to political figures and events

    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
    2:0.09
    3:0.08
    4:0.38
    5:0.03
    6:0.06
    7:0.10
    8:0.04
    9:0.03
    10:0.06
    11:0.05
    Negative Logits
     clause
    -1.69
    iffs
    -1.54
     duplication
    -1.54
     disconnect
    -1.54
     overlap
    -1.51
     depletion
    -1.51
     intervals
    -1.50
     disparity
    -1.47
     clauses
    -1.47
     consolidation
    -1.46
    POSITIVE LOGITS
    irable
    1.96
     obedient
    1.79
     happiest
    1.71
     Aware
    1.60
    onomous
    1.59
    odynam
    1.59
    pires
    1.55
     safest
    1.54
    ologically
    1.53
    ocre
    1.51
    Activations Density 0.078%

    No Known Activations