Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22602
    Prev
    Next
    INDEX
    Explanations

    phrases related to living at home after graduation

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

    warnings or cautions against certain behaviors

    oai_token-act-pair · gpt-4o-miniTriggered 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
    0:0.07
    1:0.08
    2:0.08
    3:0.08
    4:0.07
    5:0.08
    6:0.08
    7:0.09
    8:0.09
    9:0.08
    10:0.07
    11:0.08
    Negative Logits
     ;;
    -1.39
     Lys
    -1.38
    sequ
    -1.37
    doms
    -1.35
     DUP
    -1.34
    rawdownloadcloneembedreportprint
    -1.33
    hent
    -1.31
    Wiki
    -1.29
     Liberal
    -1.28
     voic
    -1.27
    POSITIVE LOGITS
    ItemThumbnailImage
    1.58
    yssey
    1.55
    mosp
    1.46
    phabet
    1.43
    Pixel
    1.41
    uminum
    1.33
     unbeliev
    1.30
    adena
    1.30
     analogy
    1.29
    itect
    1.29
    Activations Density 0.000%

    No Known Activations