© 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. 10812
    Prev
    Next
    INDEX
    Explanations

    terms related to performance metrics and attributes in technical or creative contexts

    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
    0:0.03
    1:0.01
    2:0.03
    3:0.49
    4:0.03
    5:0.06
    6:0.03
    7:0.06
    8:0.03
    9:0.02
    10:0.08
    11:0.08
    Negative Logits
     paralle
    -2.63
     chancellor
    -2.58
     senate
    -2.37
     disinteg
    -2.33
     coales
    -2.32
     despair
    -2.31
     intersect
    -2.31
     tranqu
    -2.31
     crest
    -2.31
     aust
    -2.27
    POSITIVE LOGITS
     Needs
    4.45
     Uses
    4.26
     Costs
    4.18
     Emails
    4.16
     Claims
    4.16
     Practices
    4.09
     Dates
    4.08
     Appearance
    4.06
     Dating
    4.03
     Checks
    4.03
    Activations Density 1.042%

    No Known Activations