© 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. 17198
    Prev
    Next
    INDEX
    Explanations

    names of individuals and places that may be relevant to a news context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.05
    1:0.38
    2:0.02
    3:0.03
    4:0.02
    5:0.27
    6:0.03
    7:0.01
    8:0.03
    9:0.05
    10:0.03
    11:0.02
    Negative Logits
     Airbnb
    -1.84
    ected
    -1.73
    accompan
    -1.72
     Kraken
    -1.67
     ABC
    -1.66
     iPads
    -1.65
     transitioning
    -1.63
     Directions
    -1.63
     conce
    -1.60
     NBC
    -1.57
    POSITIVE LOGITS
    n
    2.72
    b
    2.65
    d
    2.60
    t
    2.53
    a
    2.52
    q
    2.50
    aq
    2.48
    f
    2.48
    m
    2.42
    dx
    2.42
    Activations Density 0.063%

    No Known Activations