© 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. 13400
    Prev
    Next
    INDEX
    Explanations

    fields and messages typically associated with software development, specifically related to errors and code generation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    structured data and error-related information

    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
    0:0.05
    1:0.15
    2:0.11
    3:0.06
    4:0.05
    5:0.06
    6:0.11
    7:0.08
    8:0.08
    9:0.05
    10:0.08
    11:0.07
    Negative Logits
    eredith
    -1.30
    eday
    -1.23
    iko
    -1.11
     Imran
    -1.08
    uala
    -1.08
     Abbas
    -1.07
    arnaev
    -1.07
    achus
    -1.06
    aterasu
    -1.04
    banks
    -1.03
    POSITIVE LOGITS
    "],
    1.56
    >)
    1.53
    "]
    1.48
    "))
    1.46
    ":{"
    1.35
    ":-
    1.32
    ":"
    1.31
    ":"","
    1.30
    "]=>
    1.25
    \":
    1.22
    Activations Density 0.004%

    No Known Activations