© 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. 9-ATT-KK
    11. 7361
    Prev
    Next
    INDEX
    Explanations

    the presence of functions and calculations in a programming or algorithmic context

    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
    0:0.19
    1:0.04
    2:0.08
    3:0.05
    4:0.05
    5:0.05
    6:0.16
    7:0.06
    8:0.04
    9:0.16
    10:0.02
    11:0.04
    Negative Logits
     Paran
    -3.81
     chapel
    -3.53
     Crus
    -3.47
    Scar
    -3.39
     Seasons
    -3.35
     Antiqu
    -3.29
     Parks
    -3.28
     Cedar
    -3.22
     Wraith
    -3.19
     Scarlet
    -3.14
    POSITIVE LOGITS
     Input
    7.39
    Input
    7.28
     input
    7.18
    input
    7.15
     inputs
    6.67
    Output
    6.24
    output
    6.22
     Output
    6.15
     output
    5.98
     outputs
    5.87
    Activations Density 0.025%

    No Known Activations