© 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. 9-ATT-KK
    11. 13870
    Prev
    Next
    INDEX
    Explanations

    specific punctuation and formatting indicating names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.40
    2:0.04
    3:0.05
    4:0.05
    5:0.04
    6:0.07
    7:0.04
    8:0.04
    9:0.09
    10:0.05
    11:0.04
    Negative Logits
    iqueness
    -3.23
    INT
    -3.02
     sidx
    -2.91
    iencies
    -2.84
    itton
    -2.75
    IE
    -2.58
    isen
    -2.51
    emies
    -2.49
    ITION
    -2.47
    156
    -2.46
    POSITIVE LOGITS
     1973
    4.15
     1974
    4.12
     73
    4.12
     74
    3.72
     72
    3.67
    1974
    3.43
     1972
    3.36
     1976
    3.30
    1973
    3.26
     1975
    3.25
    Activations Density 0.001%

    No Known Activations