© 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. 46452
    Prev
    Next
    INDEX
    Explanations

    instances of combining elements or ideas into cohesive units

    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
    2:0.07
    3:0.11
    4:0.09
    5:0.03
    6:0.02
    7:0.41
    8:0.03
    9:0.03
    10:0.05
    11:0.07
    Negative Logits
    PLIED
    -1.96
    Critical
    -1.64
    Discuss
    -1.64
     aspire
    -1.62
    2019
    -1.56
     msec
    -1.52
    シャ
    -1.50
    ighth
    -1.47
    AIR
    -1.45
    ace
    -1.44
    POSITIVE LOGITS
     ethn
    1.46
     reorgan
    1.43
    isd
    1.40
     powd
    1.39
     flora
    1.38
    isine
    1.38
     fabric
    1.37
     chronological
    1.32
     cruelty
    1.31
     blending
    1.31
    Activations Density 0.015%

    No Known Activations