© 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. 8807
    Prev
    Next
    INDEX
    Explanations

    recommendations for products or resources

    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
    0:0.01
    1:0.01
    2:0.04
    3:0.11
    4:0.24
    5:0.02
    6:0.13
    7:0.23
    8:0.05
    9:0.03
    10:0.04
    11:0.04
    Negative Logits
     deficit
    -1.47
    isec
    -1.45
     milliseconds
    -1.43
     objection
    -1.38
     relation
    -1.37
     halfway
    -1.36
    obs
    -1.34
     contradiction
    -1.33
    */(
    -1.29
     ­
    -1.29
    POSITIVE LOGITS
    illet
    1.52
     Enhancement
    1.45
    inen
    1.45
    otin
    1.41
    tsky
    1.39
    ajo
    1.35
    series
    1.32
     IPM
    1.32
    saf
    1.31
    fen
    1.28
    Activations Density 0.006%

    No Known Activations