© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 13567
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific perspective or viewpoint

    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
    0:0.04
    1:0.03
    2:0.18
    3:0.07
    4:0.30
    5:0.07
    6:0.02
    7:0.02
    8:0.06
    9:0.07
    10:0.06
    11:0.03
    Negative Logits
    ws
    -1.50
     bom
    -1.44
     reconc
    -1.42
    rew
    -1.40
    ples
    -1.39
     indic
    -1.38
     actionGroup
    -1.36
     appl
    -1.35
     aux
    -1.34
     todd
    -1.33
    POSITIVE LOGITS
     fame
    1.50
    -------
    1.46
    spection
    1.41
    +++
    1.39
    heimer
    1.37
     Despair
    1.36
     Desire
    1.36
    chuk
    1.34
     filmmaking
    1.34
     Defeat
    1.34
    Activations Density 0.003%

    No Known Activations