© 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. 46722
    Prev
    Next
    INDEX
    Explanations

    prominent names or entities

    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
    1:0.08
    2:0.05
    3:0.15
    4:0.05
    5:0.18
    6:0.08
    7:0.02
    8:0.18
    9:0.05
    10:0.04
    11:0.03
    Negative Logits
    bound
    -1.59
     meas
    -1.44
     BALL
    -1.35
    UCT
    -1.33
     unsur
    -1.33
    Reviewed
    -1.33
     Broad
    -1.29
     bound
    -1.29
     methamphetamine
    -1.27
     lightly
    -1.26
    POSITIVE LOGITS
    ixel
    2.04
    yre
    1.86
    idays
    1.75
    ")
    1.74
    .")
    1.73
    inese
    1.68
    ").
    1.67
    inas
    1.66
    "),
    1.61
    isoft
    1.59
    Activations Density 0.012%

    No Known Activations