© 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. 4826
    Prev
    Next
    INDEX
    Explanations

    instances of numbers and statistics

    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
    0:0.25
    1:0.02
    2:0.02
    3:0.16
    4:0.07
    5:0.08
    6:0.01
    7:0.11
    8:0.02
    9:0.01
    10:0.13
    11:0.06
    Negative Logits
     diction
    -2.50
     renov
    -2.41
     coordin
    -2.35
     balcon
    -2.30
     subsid
    -2.29
     incom
    -2.25
     laboratories
    -2.24
     penet
    -2.24
     consultants
    -2.21
     ambul
    -2.16
    POSITIVE LOGITS
     Shares
    3.59
     Share
    3.20
    Pin
    2.88
     Emblem
    2.58
     Tweet
    2.46
    share
    2.41
     Pin
    2.40
    Share
    2.35
     Snap
    2.34
     Flickr
    2.30
    Activations Density 0.001%

    No Known Activations