© 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. 2-ATT-KK
    11. 22572
    Prev
    Next
    INDEX
    Explanations

    timestamps and numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    information technology-related terms such as "microservices," "boundaries," and "delivery cycle."

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.06
    2:0.16
    3:0.06
    4:0.04
    5:0.07
    6:0.04
    7:0.04
    8:0.11
    9:0.15
    10:0.08
    11:0.03
    Negative Logits
     Byte
    -1.21
     PLoS
    -1.19
     biome
    -1.15
     pse
    -1.15
     anat
    -1.11
     ¶
    -1.10
    ccording
    -1.10
     federation
    -1.10
     habit
    -1.09
     feder
    -1.08
    POSITIVE LOGITS
    200000
    1.55
    iversary
    1.25
    【
    1.24
     Crowley
    1.17
    WARD
    1.16
    trial
    1.15
     runway
    1.13
    daq
    1.11
     curtain
    1.10
    WOR
    1.10
    Activations Density 0.037%

    No Known Activations