© 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. 8881
    Prev
    Next
    INDEX
    Explanations

    concrete identifiers or data points related to technology and updates

    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
    0:0.10
    1:0.28
    2:0.05
    3:0.04
    4:0.03
    5:0.22
    6:0.03
    7:0.02
    8:0.05
    9:0.05
    10:0.04
    11:0.03
    Negative Logits
     Manit
    -1.75
     invent
    -1.66
    isen
    -1.65
    chel
    -1.65
     Carmen
    -1.60
    entin
    -1.60
     err
    -1.57
     Med
    -1.54
     Cater
    -1.53
    mort
    -1.52
    POSITIVE LOGITS
    +
    3.25
    +.
    3.12
    +,
    3.02
    +)
    2.86
    +=
    2.73
    ||
    2.39
     +/-
    2.37
    ++
    2.33
    ±
    2.24
    -.
    2.16
    Activations Density 0.003%

    No Known Activations