© 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. 41036
    Prev
    Next
    INDEX
    Explanations

    references to data sources or institutions

    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
    0:0.01
    1:0.02
    2:0.05
    3:0.06
    4:0.10
    5:0.02
    6:0.03
    7:0.37
    8:0.02
    9:0.02
    10:0.15
    11:0.11
    Negative Logits
    UGH
    -1.49
     grate
    -1.45
    eas
    -1.36
     disagree
    -1.36
    laughter
    -1.35
     metaphor
    -1.34
     uncond
    -1.32
    ++++++++
    -1.32
     analogy
    -1.31
     refrain
    -1.31
    POSITIVE LOGITS
     Nielsen
    1.52
     census
    1.51
    wn
    1.49
     Population
    1.45
    ��
    1.40
     datasets
    1.38
     collections
    1.35
     batches
    1.35
     population
    1.34
     GDP
    1.34
    Activations Density 0.029%

    No Known Activations