© 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. 8285
    Prev
    Next
    INDEX
    Explanations

    references to numerical values and reported statistics

    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
    1:0.13
    2:0.06
    3:0.05
    4:0.04
    5:0.04
    6:0.17
    7:0.04
    8:0.02
    9:0.30
    10:0.02
    11:0.02
    Negative Logits
     Emerson
    -4.12
     Schr
    -3.45
     Compton
    -3.35
     Brah
    -3.31
     Hayward
    -3.27
     Arkham
    -3.25
     Schne
    -3.22
    cientious
    -3.22
     GOODMAN
    -3.21
     Berger
    -3.14
    POSITIVE LOGITS
    lost
    4.87
     lose
    4.71
     Lost
    4.65
    Lost
    4.52
     lost
    4.16
     Loss
    4.08
     Lose
    4.08
    loss
    3.98
     loses
    3.97
     losing
    3.92
    Activations Density 0.005%

    No Known Activations