© 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. 7282
    Prev
    Next
    INDEX
    Explanations

    phrases indicating skepticism, concern, or disbelief about various topics

    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
    0:0.02
    1:0.25
    2:0.10
    3:0.05
    4:0.02
    5:0.04
    6:0.08
    7:0.07
    8:0.07
    9:0.07
    10:0.07
    11:0.13
    Negative Logits
    emn
    -1.41
    jug
    -1.39
    obo
    -1.37
    psey
    -1.33
    Merit
    -1.32
    rongh
    -1.30
    )</
    -1.28
    uci
    -1.27
    assadors
    -1.27
    reet
    -1.26
    POSITIVE LOGITS
     nor
    1.64
     except
    1.50
     anymore
    1.46
     unless
    1.42
    except
    1.36
    SourceFile
    1.31
     abnormal
    1.28
    sis
    1.19
    unless
    1.19
     necessarily
    1.19
    Activations Density 0.017%

    No Known Activations