© 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. 34631
    Prev
    Next
    INDEX
    Explanations

    terms related to failures, malfunctions, or breaks in systems and materials

    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
    0:0.03
    1:0.01
    2:0.16
    3:0.12
    4:0.09
    5:0.04
    6:0.03
    7:0.04
    8:0.06
    9:0.06
    10:0.19
    11:0.10
    Negative Logits
    ourt
    -1.44
    ijah
    -1.41
    icent
    -1.39
    senal
    -1.38
    regon
    -1.34
    orthy
    -1.30
     Blackwell
    -1.30
     politic
    -1.30
     bilingual
    -1.29
    ici
    -1.29
    POSITIVE LOGITS
     uncontroll
    1.77
     spores
    1.67
    aneously
    1.66
     molecules
    1.64
     decay
    1.62
     behaves
    1.60
     bursts
    1.59
     disappears
    1.58
     equilibrium
    1.56
     deposited
    1.56
    Activations Density 0.399%

    No Known Activations