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. 7-ATT-KK
    6. 9324
    Prev
    Next
    INDEX
    Explanations

    instances of replacement or substitution in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.06
    2:0.02
    3:0.16
    4:0.12
    5:0.10
    6:0.04
    7:0.03
    8:0.27
    9:0.06
    10:0.01
    11:0.02
    Negative Logits
     overview
    -1.65
     gif
    -1.63
     disclosure
    -1.59
     approached
    -1.57
     describ
    -1.54
     relate
    -1.53
    onnaissance
    -1.52
     photograp
    -1.51
     disse
    -1.51
     entit
    -1.50
    POSITIVE LOGITS
     replacements
    2.19
     replacing
    2.08
     replacement
    2.02
     replace
    1.90
    Repl
    1.89
    solete
    1.81
     Replace
    1.80
     Replacement
    1.77
     retiring
    1.70
    rano
    1.69
    Activations Density 0.056%

    No Known Activations