© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-ATT-KK
    11. 23200
    Prev
    Next
    INDEX
    Explanations

    information relating to geographical locations, agriculture, economics, and politics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    numerical values and terms related to measurements or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.02
    2:0.33
    3:0.13
    4:0.09
    5:0.07
    6:0.02
    7:0.01
    8:0.03
    9:0.09
    10:0.03
    11:0.01
    Negative Logits
     Pagan
    -1.57
     Anita
    -1.50
     Eleanor
    -1.43
     Levant
    -1.36
    abilia
    -1.34
     Shank
    -1.31
     Ars
    -1.30
     Akin
    -1.28
    nce
    -1.28
     Ernst
    -1.27
    POSITIVE LOGITS
    undred
    1.73
     apiece
    1.67
    cyl
    1.54
    fif
    1.53
    ousand
    1.51
    quad
    1.44
    ighters
    1.44
    ottest
    1.43
    secut
    1.42
    inch
    1.36
    Activations Density 0.045%

    No Known Activations