© 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. 17936
    Prev
    Next
    INDEX
    Explanations

    the author's name, particularly "Jason Ditz"

    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
    0:0.18
    1:0.02
    2:0.03
    3:0.19
    4:0.07
    5:0.06
    6:0.03
    7:0.05
    8:0.02
    9:0.01
    10:0.15
    11:0.13
    Negative Logits
     Documents
    -2.41
     Examination
    -2.37
     Hearing
    -2.31
     Witnesses
    -2.26
     Neutral
    -2.24
    ":""},{"
    -2.24
     Television
    -2.17
     Supporters
    -2.14
    :\
    -2.13
     \"
    -2.12
    POSITIVE LOGITS
    alted
    2.64
     fab
    2.32
     pist
    2.25
     posts
    2.05
    posts
    2.00
     pope
    1.99
     crafts
    1.99
     piston
    1.95
     rabbi
    1.91
    blogspot
    1.90
    Activations Density 0.000%

    No Known Activations