© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 53
    Prev
    Next
    INDEX
    Explanations

    gerund forms of verbs indicating actions or activities

    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
    0:0.02
    1:0.03
    2:0.06
    3:0.08
    4:0.09
    5:0.02
    6:0.40
    7:0.06
    8:0.03
    9:0.03
    10:0.07
    11:0.06
    Negative Logits
     appell
    -1.28
    raltar
    -1.24
    ught
    -1.20
     Brotherhood
    -1.19
     Farms
    -1.15
    �
    -1.12
    utan
    -1.12
    tarians
    -1.12
     indebted
    -1.10
     Toledo
    -1.09
    POSITIVE LOGITS
    oresc
    1.55
    wordpress
    1.31
    meier
    1.25
    atche
    1.17
    nova
    1.17
    eus
    1.17
     tyr
    1.16
    uberty
    1.15
    rast
    1.15
    ouver
    1.14
    Activations Density 0.050%

    No Known Activations