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. 3-ATT-KK
    6. 10203
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and timelines in a narrative context

    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
    0:0.02
    1:0.04
    2:0.15
    3:0.18
    4:0.02
    5:0.04
    6:0.07
    7:0.08
    8:0.17
    9:0.05
    10:0.08
    11:0.04
    Negative Logits
    isms
    -1.07
     buttons
    -1.03
    inctions
    -1.03
     negativity
    -1.02
     labels
    -0.98
     candles
    -0.97
     spoilers
    -0.97
     trolls
    -0.96
     secrets
    -0.95
    istas
    -0.94
    POSITIVE LOGITS
     midst
    1.51
     vein
    1.41
     vicinity
    1.37
     guise
    1.33
    soDeliveryDate
    1.17
     courtyard
    1.13
     borough
    1.12
     Heights
    1.10
     suburbs
    1.08
     Borough
    1.08
    Activations Density 0.282%

    No Known Activations