© 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. 42137
    Prev
    Next
    INDEX
    Explanations

    attributes, measures, or characteristics related to various topics or data points

    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
    2:0.08
    3:0.05
    4:0.07
    5:0.02
    6:0.39
    7:0.09
    8:0.02
    9:0.03
    10:0.10
    11:0.06
    Negative Logits
    rawdownloadcloneembedreportprint
    -1.48
    entimes
    -1.40
    velt
    -1.38
    =]
    -1.33
    icut
    -1.28
    hower
    -1.28
    alsh
    -1.28
    idan
    -1.24
    issance
    -1.24
    enn
    -1.24
    POSITIVE LOGITS
    units
    1.52
    Integer
    1.49
     allocations
    1.41
     predict
    1.37
     Cthulhu
    1.33
    abytes
    1.25
     Numbers
    1.24
     pts
    1.21
     indicators
    1.20
     predicted
    1.19
    Activations Density 0.015%

    No Known Activations