© 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. 25791
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the character "ľ" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.12
    1:0.04
    2:0.16
    3:0.05
    4:0.03
    5:0.08
    6:0.16
    7:0.03
    8:0.06
    9:0.06
    10:0.08
    11:0.06
    Negative Logits
     […]
    -1.67
    ....
    -1.51
    "}
    -1.44
     [...]
    -1.41
    ?!"
    -1.31
     seiz
    -1.29
     central
    -1.28
     gust
    -1.28
     -----
    -1.27
     pinch
    -1.26
    POSITIVE LOGITS
    tta
    1.63
    months
    1.60
    senal
    1.57
    yrights
    1.51
    clips
    1.50
    venth
    1.48
     reperto
    1.45
    Reason
    1.44
    thouse
    1.42
     selves
    1.41
    Activations Density 0.061%

    No Known Activations