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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19376
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and game-related terms

    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
    0:0.31
    1:0.04
    2:0.07
    3:0.06
    4:0.06
    5:0.08
    6:0.05
    7:0.03
    8:0.04
    9:0.07
    10:0.08
    11:0.07
    Negative Logits
    uyomi
    -1.96
     princ
    -1.74
     Corpus
    -1.71
     GOODMAN
    -1.60
     Alphabet
    -1.57
     enthusi
    -1.56
    CLASSIFIED
    -1.54
     Borders
    -1.54
     Progressive
    -1.52
     conven
    -1.50
    POSITIVE LOGITS
    7
    2.65
    9
    2.56
    8
    2.56
    6
    2.47
    0
    2.44
    5
    2.30
    1
    2.30
    3
    2.30
    2
    2.28
    10
    2.16
    Activations Density 0.004%

    No Known Activations