© 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. 4804
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences that indicate the potential for significant effects or consequences

    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
    1:0.09
    2:0.06
    3:0.09
    4:0.09
    5:0.07
    6:0.09
    7:0.08
    8:0.08
    9:0.06
    10:0.08
    11:0.09
    Negative Logits
     grav
    -3.06
     tink
    -2.91
     plur
    -2.81
     detached
    -2.81
     hollow
    -2.69
     balk
    -2.68
     chrom
    -2.59
     vacuum
    -2.57
     bread
    -2.56
     gloom
    -2.56
    POSITIVE LOGITS
     Rated
    3.39
     Evaluation
    3.17
     Relief
    2.95
     Performance
    2.85
     Ranked
    2.85
     Prix
    2.81
     Shaun
    2.79
     Encounter
    2.77
     Anthem
    2.73
     Protection
    2.68
    Activations Density 0.000%

    No Known Activations