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. 5-ATT-KK
    6. 7456
    Prev
    Next
    INDEX
    Explanations

    recurring patterns in various contexts

    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
    0:0.01
    1:0.02
    2:0.06
    3:0.04
    4:0.07
    5:0.02
    6:0.07
    7:0.47
    8:0.02
    9:0.03
    10:0.08
    11:0.06
    Negative Logits
    kamp
    -1.71
     uncond
    -1.37
    orthy
    -1.35
    戦
    -1.31
     Asked
    -1.28
    leased
    -1.26
    nai
    -1.26
    required
    -1.26
    zai
    -1.25
     wee
    -1.22
    POSITIVE LOGITS
     patterns
    1.83
     behavior
    1.69
    gradient
    1.64
     behaviour
    1.64
    Pattern
    1.62
     pattern
    1.62
     strand
    1.60
     Patterns
    1.59
     behaviors
    1.50
    destruct
    1.49
    Activations Density 0.010%

    No Known Activations