© 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. 10330
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with data structures and operations

    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
    0:0.07
    1:0.22
    2:0.05
    3:0.16
    4:0.05
    5:0.14
    6:0.05
    7:0.09
    8:0.02
    9:0.03
    10:0.04
    11:0.02
    Negative Logits
    anty
    -3.11
     promptly
    -2.65
    facts
    -2.46
     Upton
    -2.30
    whatever
    -2.30
     remission
    -2.22
     atro
    -2.20
     Depot
    -2.15
     sellers
    -2.10
    ogo
    -2.07
    POSITIVE LOGITS
    Param
    2.88
    Script
    2.77
    Calling
    2.66
     func
    2.53
     xml
    2.49
     lang
    2.49
    Java
    2.46
     ns
    2.43
    Known
    2.39
    lua
    2.37
    Activations Density 0.003%

    No Known Activations