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. 3-ATT-KK
    6. 8571
    Prev
    Next
    INDEX
    Explanations

    instances of the word "re"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.05
    2:0.13
    3:0.13
    4:0.01
    5:0.04
    6:0.15
    7:0.13
    8:0.08
    9:0.09
    10:0.05
    11:0.07
    Negative Logits
     wors
    -1.26
     Grape
    -1.10
    isc
    -1.10
     lasts
    -1.05
     plum
    -1.05
     deterior
    -1.04
     turnaround
    -1.01
    heres
    -0.97
     Corinth
    -0.96
     fruitful
    -0.95
    POSITIVE LOGITS
     WATCHED
    1.36
    */(
    1.31
    gey
    1.26
    soDeliveryDate
    1.26
     Butt
    1.24
    din
    1.24
     Dating
    1.20
     Chains
    1.16
    uder
    1.14
    龍�
    1.14
    Activations Density 0.028%

    No Known Activations