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. 3-ATT-KK
    6. 10277
    Prev
    Next
    INDEX
    Explanations

    references to parts or components in a context related to systems or structures

    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
    0:0.05
    1:0.07
    2:0.24
    3:0.05
    4:0.02
    5:0.03
    6:0.08
    7:0.06
    8:0.06
    9:0.08
    10:0.13
    11:0.08
    Negative Logits
     DRAG
    -1.13
     staples
    -1.08
     propensity
    -1.05
     Nerd
    -1.03
     swapping
    -0.99
     poems
    -0.97
     skew
    -0.96
     coats
    -0.96
     drawings
    -0.95
     notebooks
    -0.95
    POSITIVE LOGITS
    qqa
    1.13
    twitch
    1.10
    wagen
    1.10
    Downloadha
    1.10
    cise
    1.07
    canon
    1.05
    ortium
    1.05
    third
    1.03
    clusive
    1.03
    adow
    1.03
    Activations Density 0.017%

    No Known Activations