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. 2-ATT-KK
    6. 13845
    Prev
    Next
    INDEX
    Explanations

    proper nouns and phrases related to political events or figures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.04
    2:0.29
    3:0.05
    4:0.23
    5:0.04
    6:0.02
    7:0.02
    8:0.05
    9:0.06
    10:0.05
    11:0.02
    Negative Logits
    Methods
    -1.31
     Trop
    -1.29
     contrace
    -1.28
     Ribbon
    -1.13
    Spons
    -1.13
     Extensions
    -1.12
     Supplemental
    -1.11
    Specific
    -1.10
    GROUND
    -1.09
    BUG
    -1.09
    POSITIVE LOGITS
    peat
    1.61
    omial
    1.41
     imprint
    1.31
     filament
    1.26
    lein
    1.25
     horn
    1.20
     trout
    1.19
     imitation
    1.19
    oshop
    1.18
     pen
    1.18
    Activations Density 0.008%

    No Known Activations