© 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. 37382
    Prev
    Next
    INDEX
    Explanations

    content that discusses the significance or implications of specific ideas or information

    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
    1:0.02
    2:0.12
    3:0.32
    4:0.07
    5:0.03
    6:0.03
    7:0.10
    8:0.04
    9:0.06
    10:0.07
    11:0.06
    Negative Logits
    apsed
    -1.57
     PTS
    -1.51
     Chal
    -1.49
     (£
    -1.49
    hner
    -1.41
     Yen
    -1.41
     Lyons
    -1.39
     Alexandra
    -1.37
    stood
    -1.37
    quished
    -1.37
    POSITIVE LOGITS
    ?).
    1.73
     ;)
    1.68
     asses
    1.67
    ...)
    1.66
     kinda
    1.66
     :)
    1.61
    ?)
    1.60
    ?),
    1.57
     myself
    1.57
     guys
    1.55
    Activations Density 0.009%

    No Known Activations