Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 22342
    Prev
    Next
    INDEX
    Explanations

    specific years and dates mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered 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
    0:0.05
    1:0.04
    2:0.10
    3:0.07
    4:0.18
    5:0.11
    6:0.05
    7:0.03
    8:0.06
    9:0.11
    10:0.10
    11:0.03
    Negative Logits
     Endless
    -1.57
     endless
    -1.36
    drops
    -1.34
    dream
    -1.31
    ritch
    -1.28
    oran
    -1.27
    war
    -1.26
    acha
    -1.24
    ��
    -1.23
    endish
    -1.23
    POSITIVE LOGITS
    quickShipAvailable
    1.64
     IST
    1.38
     REUTERS
    1.36
     EDT
    1.36
     FTA
    1.33
    displayText
    1.32
     PDT
    1.31
     UTC
    1.26
     amended
    1.26
     PST
    1.24
    Activations Density 0.035%

    No Known Activations