© 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. 3235
    Prev
    Next
    INDEX
    Explanations

    phrases and words indicating possession or belonging

    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
    1:0.02
    2:0.05
    3:0.05
    4:0.07
    5:0.04
    6:0.10
    7:0.32
    8:0.03
    9:0.04
    10:0.13
    11:0.08
    Negative Logits
     horizont
    -1.84
     acceleration
    -1.78
     magnification
    -1.75
     disadvantage
    -1.74
     vacancy
    -1.70
     simultane
    -1.68
     candidacy
    -1.64
     dimensional
    -1.62
     ceilings
    -1.61
     budgetary
    -1.60
    POSITIVE LOGITS
    landers
    1.73
    ingle
    1.53
    urtles
    1.50
     Chocobo
    1.48
    acus
    1.46
     Guer
    1.41
    ensis
    1.41
    onyms
    1.40
    ordes
    1.40
     Europeans
    1.40
    Activations Density 0.001%

    No Known Activations