© 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. 18557
    Prev
    Next
    INDEX
    Explanations

    occurrences of names, particularly those related to places or significant nouns

    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
    0:0.03
    1:0.03
    2:0.06
    3:0.04
    4:0.04
    5:0.03
    6:0.52
    7:0.03
    8:0.03
    9:0.04
    10:0.06
    11:0.04
    Negative Logits
     slump
    -1.46
     Olympia
    -1.30
    WHERE
    -1.24
     slightest
    -1.24
     skew
    -1.21
     erection
    -1.21
     roadside
    -1.19
     Mazda
    -1.19
     horizon
    -1.18
     rolls
    -1.18
    POSITIVE LOGITS
    andise
    1.80
    etary
    1.64
    merce
    1.56
    andowski
    1.55
    ideo
    1.54
    export
    1.45
    culosis
    1.44
    oyer
    1.41
    ordes
    1.40
    ophen
    1.40
    Activations Density 0.035%

    No Known Activations