© 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. 557
    Prev
    Next
    INDEX
    Explanations

    references to physical positions or orientations of individuals and objects

    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
    0:0.02
    1:0.01
    2:0.13
    3:0.06
    4:0.12
    5:0.02
    6:0.09
    7:0.22
    8:0.03
    9:0.04
    10:0.11
    11:0.08
    Negative Logits
     Cosponsors
    -2.04
     newsletters
    -1.57
    �
    -1.53
    CLASS
    -1.53
    phasis
    -1.44
    CONT
    -1.43
    ocus
    -1.40
     influ
    -1.39
    Specific
    -1.37
    conom
    -1.33
    POSITIVE LOGITS
     lam
    1.83
    rium
    1.68
     cradle
    1.60
     halves
    1.55
     shoulders
    1.53
     pedest
    1.52
     bushes
    1.48
     Crescent
    1.48
     shoulder
    1.44
     tray
    1.43
    Activations Density 0.004%

    No Known Activations