© 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. 15728
    Prev
    Next
    INDEX
    Explanations

    data related to rankings, performance metrics, and statistical comparisons in various 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
    0:0.05
    1:0.01
    2:0.06
    3:0.36
    4:0.02
    5:0.10
    6:0.02
    7:0.03
    8:0.02
    9:0.01
    10:0.24
    11:0.02
    Negative Logits
    hai
    -2.14
    Sov
    -2.00
     grandfather
    -1.83
    stals
    -1.77
    zees
    -1.75
     revert
    -1.73
    itars
    -1.72
    irez
    -1.71
    assad
    -1.70
     vest
    -1.69
    POSITIVE LOGITS
     rankings
    2.93
     category
    2.75
     categories
    2.67
     ranking
    2.59
     ratings
    2.48
     Ratings
    2.47
     metrics
    2.43
     Ranking
    2.41
     rating
    2.36
     Rankings
    2.29
    Activations Density 0.303%

    No Known Activations