© 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. 45331
    Prev
    Next
    INDEX
    Explanations

    significant quantities and qualities of content related to unique or specialized topics

    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
    2:0.12
    3:0.16
    4:0.10
    5:0.06
    6:0.08
    7:0.05
    8:0.08
    9:0.07
    10:0.11
    11:0.07
    Negative Logits
     Yesterday
    -1.49
    erent
    -1.49
    again
    -1.47
    nesday
    -1.46
    piracy
    -1.46
    Leaks
    -1.45
    Lee
    -1.43
     Again
    -1.40
    election
    -1.39
    mun
    -1.37
    POSITIVE LOGITS
     catchy
    1.63
     pulse
    1.61
     recognizable
    1.57
     pedigree
    1.51
     twist
    1.47
     ribbon
    1.46
     tempo
    1.44
     backbone
    1.44
     charm
    1.41
     shimmer
    1.41
    Activations Density 0.149%

    No Known Activations