© 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. 46323
    Prev
    Next
    INDEX
    Explanations

    key concepts related to proposals and political processes

    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
    0:0.01
    1:0.01
    2:0.27
    3:0.15
    4:0.11
    5:0.04
    6:0.04
    7:0.08
    8:0.05
    9:0.04
    10:0.08
    11:0.06
    Negative Logits
    hid
    -1.83
    dylib
    -1.67
    jad
    -1.43
    ymes
    -1.40
    @#&
    -1.39
    aleb
    -1.33
    ancies
    -1.32
    uscript
    -1.31
    ournals
    -1.28
    errors
    -1.28
    POSITIVE LOGITS
     whichever
    1.61
     tomorrow
    1.57
     ASAP
    1.57
     someday
    1.56
     whoever
    1.46
     eternity
    1.45
     sooner
    1.43
    morrow
    1.38
    !!!!
    1.38
     achievable
    1.37
    Activations Density 0.363%

    No Known Activations