© 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. 3-ATT-KK
    11. 8701
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to measurements and settings, particularly in scientific and technological contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.37
    1:0.03
    2:0.03
    3:0.03
    4:0.13
    5:0.05
    6:0.06
    7:0.06
    8:0.02
    9:0.03
    10:0.09
    11:0.04
    Negative Logits
    arna
    -1.38
    apons
    -1.31
    ailable
    -1.31
    mun
    -1.30
    istani
    -1.25
    olkien
    -1.25
    orned
    -1.23
    arnaev
    -1.21
    advertisement
    -1.19
    estern
    -1.18
    POSITIVE LOGITS
     gradient
    1.40
     increments
    1.36
     ratios
    1.35
     amplitude
    1.35
     intervals
    1.34
     drift
    1.34
     fluctuations
    1.33
     thresholds
    1.33
     extremes
    1.32
     ratings
    1.30
    Activations Density 0.234%

    No Known Activations