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. 7-ATT-KK
    6. 9043
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations and entities involved in controversies or legal matters

    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
    0:0.19
    1:0.03
    2:0.03
    3:0.10
    4:0.07
    5:0.11
    6:0.02
    7:0.02
    8:0.19
    9:0.15
    10:0.01
    11:0.01
    Negative Logits
    entimes
    -2.04
    etheless
    -1.75
     persuasion
    -1.75
     whisper
    -1.66
     uptake
    -1.63
    hun
    -1.61
     coax
    -1.60
    oneliness
    -1.60
     wow
    -1.56
    ebook
    -1.54
    POSITIVE LOGITS
     landmarks
    1.83
     finalists
    1.72
     unnamed
    1.65
     appell
    1.63
     names
    1.58
     nominees
    1.58
     fictitious
    1.50
     Annex
    1.50
    フォ
    1.50
     categories
    1.48
    Activations Density 0.028%

    No Known Activations