© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 6052
    Prev
    Next
    INDEX
    Explanations

    comments and annotations related to coding and programming concepts

    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
    1:0.17
    2:0.09
    3:0.07
    4:0.05
    5:0.07
    6:0.08
    7:0.10
    8:0.08
    9:0.05
    10:0.07
    11:0.06
    Negative Logits
    umbn
    -1.45
    yss
    -1.43
    prus
    -1.42
     photograp
    -1.40
    abwe
    -1.35
    WA
    -1.32
    anamo
    -1.28
    asca
    -1.27
    asus
    -1.27
    zik
    -1.25
    POSITIVE LOGITS
     ();
    1.38
     :=
    1.20
     ().
    1.20
     Quint
    1.14
     Supplement
    1.13
    Stack
    1.13
     +=
    1.10
    SourceFile
    1.08
     Answer
    1.08
     Declaration
    1.07
    Activations Density 0.001%

    No Known Activations