© 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 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. 43626
    Prev
    Next
    INDEX
    Explanations

    references to identified groups of individuals or entities

    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
    1:0.02
    2:0.21
    3:0.18
    4:0.15
    5:0.03
    6:0.04
    7:0.09
    8:0.04
    9:0.03
    10:0.07
    11:0.07
    Negative Logits
    ć
    -1.45
     BAS
    -1.44
    ô
    -1.44
     nm
    -1.43
    oons
    -1.43
     guiActiveUn
    -1.42
    bah
    -1.42
    idity
    -1.36
    ouch
    -1.32
     srf
    -1.28
    POSITIVE LOGITS
    eligible
    1.68
     barred
    1.49
     TAMADRA
    1.47
     deadliest
    1.39
     delinquent
    1.38
     awaiting
    1.37
    liest
    1.34
     embattled
    1.33
     quir
    1.33
    apest
    1.32
    Activations Density 0.034%

    No Known Activations