© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-ATT-KK
    11. 10302
    Prev
    Next
    INDEX
    Explanations

    instances of the character "Ċ"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.05
    2:0.05
    3:0.04
    4:0.27
    5:0.19
    6:0.05
    7:0.06
    8:0.05
    9:0.03
    10:0.03
    11:0.07
    Negative Logits
    Production
    -3.50
    Performance
    -3.27
    Initial
    -3.20
    OTHER
    -3.17
    Compar
    -3.09
    Diff
    -3.05
    isoft
    -3.05
    Development
    -2.98
    isal
    -2.98
    Summary
    -2.92
    POSITIVE LOGITS
     sob
    2.91
     kissed
    2.79
     cheered
    2.67
     raging
    2.65
     menace
    2.65
     beck
    2.56
     puff
    2.53
     �
    2.53
     choking
    2.52
     tremb
    2.50
    Activations Density 0.000%

    No Known Activations