© 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. 3-ATT-KK
    11. 11835
    Prev
    Next
    INDEX
    Explanations

    interrogative sentences, likely at the end of a text

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

    questions directed at the reader or audience

    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
    0:0.03
    1:0.08
    2:0.04
    3:0.02
    4:0.09
    5:0.40
    6:0.04
    7:0.04
    8:0.04
    9:0.08
    10:0.06
    11:0.03
    Negative Logits
    izont
    -2.19
    SourceFile
    -2.11
    ⓘ
    -2.08
     Oval
    -2.01
     cubic
    -1.97
    sonian
    -1.94
     contiguous
    -1.86
    seless
    -1.77
     intersection
    -1.76
    ixt
    -1.76
    POSITIVE LOGITS
    answer
    2.69
    answered
    2.47
     interrogation
    2.30
     Feedback
    2.22
     Response
    2.12
    Question
    2.04
    Answer
    2.02
     misunderstand
    2.02
    topic
    1.95
    respons
    1.92
    Activations Density 0.043%

    No Known Activations