© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 41592
    Prev
    Next
    INDEX
    Explanations

    instances where something is obstructing or blocking something else

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    1:0.02
    2:0.07
    3:0.05
    4:0.09
    5:0.04
    6:0.07
    7:0.23
    8:0.06
    9:0.05
    10:0.14
    11:0.09
    Negative Logits
     mastered
    -1.50
     airs
    -1.48
     strengths
    -1.47
     resumes
    -1.45
     programmed
    -1.41
    ��
    -1.40
     productivity
    -1.37
     repet
    -1.35
     wellness
    -1.32
     creative
    -1.32
    POSITIVE LOGITS
    aphael
    1.53
    iverpool
    1.49
    acas
    1.46
    oin
    1.44
    dinand
    1.40
    ongyang
    1.39
    uyomi
    1.38
    yet
    1.35
    Cas
    1.34
    ukemia
    1.33
    Activations Density 0.000%

    No Known Activations