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. 9520
    Prev
    Next
    INDEX
    Explanations

    specific terms and references related to specific groups or categories, especially in contexts involving demographics, political or social issues, and technical details

    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
    0:0.18
    1:0.04
    2:0.01
    3:0.04
    4:0.21
    5:0.04
    6:0.04
    7:0.05
    8:0.11
    9:0.03
    10:0.05
    11:0.15
    Negative Logits
    laughter
    -2.13
    someone
    -2.10
    isine
    -2.10
    cellence
    -1.87
    emphasis
    -1.87
    �
    -1.86
    ikawa
    -1.84
    omics
    -1.80
    Dialogue
    -1.76
    anship
    -1.74
    POSITIVE LOGITS
     respectively
    2.46
     portion
    2.03
     cycle
    2.02
    ottest
    1.99
     versions
    1.98
     eras
    1.97
     phases
    1.97
     respective
    1.92
    iott
    1.91
     ones
    1.90
    Activations Density 0.040%

    No Known Activations