© 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. 11843
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or hesitation

    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
    0:0.08
    1:0.03
    2:0.14
    3:0.10
    4:0.13
    5:0.05
    6:0.06
    7:0.02
    8:0.13
    9:0.10
    10:0.06
    11:0.03
    Negative Logits
    properties
    -1.23
    fram
    -1.20
    Pod
    -1.16
    ilt
    -1.16
     Semin
    -1.15
    ーティ
    -1.14
    eli
    -1.13
     backdrop
    -1.12
    achev
    -1.11
    imov
    -1.10
    POSITIVE LOGITS
     goddamn
    1.26
     Execution
    1.17
     �
    1.15
     patience
    1.12
    !:
    1.11
     Cth
    1.10
     fucking
    1.09
     suspic
    1.08
     moratorium
    1.07
     hell
    1.07
    Activations Density 0.006%

    No Known Activations