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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 7676
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure elements, particularly in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.03
    2:0.02
    3:0.04
    4:0.06
    5:0.07
    6:0.42
    7:0.04
    8:0.04
    9:0.03
    10:0.03
    11:0.16
    Negative Logits
     Colour
    -3.03
     @@
    -2.82
     Sins
    -2.79
    ��
    -2.68
     SetFontSize
    -2.59
    "},
    -2.56
    bush
    -2.46
     Added
    -2.41
     Root
    -2.38
     Shape
    -2.38
    POSITIVE LOGITS
     baggage
    2.37
    flight
    2.34
    wra
    2.32
     compet
    2.30
    ────
    2.26
     bikini
    2.25
    cler
    2.21
     salad
    2.14
    byss
    2.12
    ↵
    2.10
    Activations Density 0.118%

    No Known Activations