© 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. 41473
    Prev
    Next
    INDEX
    Explanations

    assertions or claims being made, particularly in discussions involving facts or opinions

    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
    0:0.35
    1:0.02
    2:0.04
    3:0.07
    4:0.04
    5:0.07
    6:0.02
    7:0.02
    8:0.06
    9:0.10
    10:0.11
    11:0.05
    Negative Logits
     inhab
    -1.65
    ..."
    -1.65
    Enlarge
    -1.64
    !/
    -1.57
    arium
    -1.56
    ".[
    -1.55
     occupies
    -1.54
     █
    -1.51
    !",
    -1.51
    fecture
    -1.49
    POSITIVE LOGITS
     praise
    2.00
     mention
    1.96
     acknowled
    1.95
     acknowledgement
    1.91
    FINE
    1.88
     nods
    1.87
     cynicism
    1.79
    another
    1.78
     upbeat
    1.77
    cknow
    1.74
    Activations Density 0.643%

    No Known Activations