© 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. 45440
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names and titles

    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
    0:0.08
    1:0.19
    2:0.05
    3:0.05
    4:0.04
    5:0.20
    6:0.08
    7:0.03
    8:0.04
    9:0.07
    10:0.07
    11:0.05
    Negative Logits
     horizont
    -2.03
     monop
    -1.75
     chains
    -1.53
     antim
    -1.50
     Access
    -1.48
    theless
    -1.42
     Telesc
    -1.38
    bestos
    -1.38
     sid
    -1.37
     AFL
    -1.37
    POSITIVE LOGITS
    uk
    2.04
    uchi
    2.03
    ashi
    1.89
    arro
    1.89
    akuya
    1.82
    ono
    1.80
    iji
    1.79
    eco
    1.79
    ev
    1.76
    chuk
    1.76
    Activations Density 0.003%

    No Known Activations