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. 9-ATT-KK
    6. 465
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" and look for color descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.23
    1:0.04
    2:0.11
    3:0.07
    4:0.05
    5:0.07
    6:0.08
    7:0.06
    8:0.05
    9:0.11
    10:0.06
    11:0.04
    Negative Logits
    aska
    -2.87
     Neal
    -2.81
     riding
    -2.80
    maps
    -2.73
     Tracks
    -2.72
     surf
    -2.67
    osate
    -2.63
     Niet
    -2.58
     Okin
    -2.58
    aint
    -2.58
    POSITIVE LOGITS
     bulbs
    5.21
     bulb
    5.08
     Bloom
    3.64
     Bul
    3.60
     fluorescent
    3.54
     CFL
    3.54
     Philips
    3.12
     blackmail
    3.01
    Connector
    2.99
     Stam
    2.90
    Activations Density 0.000%

    No Known Activations