© 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. 8832
    Prev
    Next
    INDEX
    Explanations

    punctuation and structured elements within sentences

    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
    1:0.03
    2:0.04
    3:0.05
    4:0.04
    5:0.04
    6:0.23
    7:0.02
    8:0.07
    9:0.29
    10:0.04
    11:0.03
    Negative Logits
     photoc
    -4.08
    Sac
    -3.96
    poral
    -3.92
    izo
    -3.80
    SP
    -3.75
    sac
    -3.75
    caps
    -3.60
     cloves
    -3.60
    ertodd
    -3.58
    cap
    -3.53
    POSITIVE LOGITS
     Allison
    10.65
     Alison
    5.59
     Ack
    5.29
     Elliott
    4.73
     Ryder
    4.38
     Lindsay
    4.32
    ison
    4.31
     LH
    4.27
     Allan
    4.19
     Ballard
    4.01
    Activations Density 0.001%

    No Known Activations