© 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. 5-ATT-KK
    11. 17286
    Prev
    Next
    INDEX
    Explanations

    Java programming constructs and patterns related to data structures and caching mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.02
    2:0.11
    3:0.13
    4:0.25
    5:0.05
    6:0.05
    7:0.04
    8:0.05
    9:0.06
    10:0.08
    11:0.07
    Negative Logits
     GOODMAN
    -1.76
    thora
    -1.75
    soType
    -1.68
    untled
    -1.64
    icans
    -1.60
    iotics
    -1.60
    ourt
    -1.52
     dstg
    -1.51
    rums
    -1.49
     jaws
    -1.48
    POSITIVE LOGITS
    ();
    1.64
    ());
    1.43
    Year
    1.36
     Dob
    1.34
    Center
    1.34
    Fighting
    1.32
     premiere
    1.31
    |
    1.28
     dw
    1.28
    Location
    1.26
    Activations Density 0.002%

    No Known Activations