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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 2736
    Prev
    Next
    INDEX
    Explanations

    specific names or identifiers within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.02
    2:0.21
    3:0.04
    4:0.05
    5:0.04
    6:0.35
    7:0.05
    8:0.04
    9:0.03
    10:0.07
    11:0.03
    Negative Logits
    sheets
    -1.60
    Topic
    -1.58
    cens
    -1.50
    packing
    -1.38
    unin
    -1.38
    ーン
    -1.37
    quartered
    -1.35
    cellaneous
    -1.34
    testers
    -1.27
    ctory
    -1.26
    POSITIVE LOGITS
     Shoes
    1.37
    oire
    1.36
    nik
    1.32
     Shine
    1.32
    Jr
    1.23
     dy
    1.21
     McGee
    1.21
     dstg
    1.19
     ric
    1.19
    Az
    1.18
    Activations Density 0.005%

    No Known Activations