© 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. 40734
    Prev
    Next
    INDEX
    Explanations

    references to specific events, bills, or timelines related to political or organizational contexts

    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
    2:0.17
    3:0.09
    4:0.18
    5:0.06
    6:0.02
    7:0.07
    8:0.09
    9:0.08
    10:0.08
    11:0.05
    Negative Logits
    �
    -0.97
    animate
    -0.84
     drown
    -0.79
    ettel
    -0.77
     voic
    -0.74
    pound
    -0.74
     brakes
    -0.74
    天
    -0.72
    inous
    -0.71
     vomit
    -0.71
    POSITIVE LOGITS
     respectively
    1.10
    $.
    1.04
    >.
    1.03
    +.
    0.99
    nesday
    0.99
    ISION
    0.97
    *.
    0.96
     ".
    0.94
    ''.
    0.90
    !.
    0.89
    Activations Density 2.770%

    No Known Activations