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. 44381
    Prev
    Next
    INDEX
    Explanations

    key phrases and structures related to comparisons and contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    2:0.17
    3:0.08
    4:0.20
    5:0.03
    6:0.05
    7:0.16
    8:0.07
    9:0.04
    10:0.06
    11:0.05
    Negative Logits
     Treasurer
    -1.81
    osponsors
    -1.67
     treasurer
    -1.60
     Reloaded
    -1.57
    andise
    -1.55
     owners
    -1.55
     propriet
    -1.49
    Site
    -1.46
     endors
    -1.46
     faithful
    -1.44
    POSITIVE LOGITS
    impact
    1.82
    htaking
    1.81
    obyl
    1.79
    posure
    1.63
    utonium
    1.60
    ngth
    1.56
    ocity
    1.54
    Downloadha
    1.52
    mouth
    1.51
    ruciating
    1.50
    Activations Density 0.002%

    No Known Activations