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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13729
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically related to people

    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
    1:0.09
    2:0.08
    3:0.08
    4:0.07
    5:0.09
    6:0.08
    7:0.07
    8:0.08
    9:0.07
    10:0.07
    11:0.08
    Negative Logits
    kell
    -1.57
    aucus
    -1.56
    ngth
    -1.54
    otos
    -1.53
    ostic
    -1.50
    iler
    -1.45
    cal
    -1.44
    irrel
    -1.43
    sembly
    -1.41
    otrop
    -1.41
    POSITIVE LOGITS
     Rouhani
    1.59
     imperialism
    1.52
     Hague
    1.52
     journalism
    1.49
     fulfil
    1.49
     disclosures
    1.45
     doors
    1.45
     Myanmar
    1.44
     broadcasters
    1.42
     ambition
    1.41
    Activations Density 0.000%

    No Known Activations