© 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. 42848
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    0:0.08
    1:0.05
    2:0.09
    3:0.09
    4:0.09
    5:0.08
    6:0.08
    7:0.08
    8:0.08
    9:0.08
    10:0.08
    11:0.07
    Negative Logits
    ��
    -2.19
     derivatives
    -1.93
     steroids
    -1.87
    aceutical
    -1.73
     Contracts
    -1.70
     GDDR
    -1.65
     economics
    -1.65
     patents
    -1.64
     technologies
    -1.64
     marketing
    -1.64
    POSITIVE LOGITS
    ipeg
    2.03
    bryce
    2.03
    externalActionCode
    1.97
    dayName
    1.93
    adelphia
    1.90
    pmwiki
    1.88
    lehem
    1.83
    psey
    1.76
    yip
    1.73
     sqor
    1.73
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.