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. 7755
    Prev
    Next
    INDEX
    Explanations

    phrases indicating challenges and opportunities related to support or assistance for various groups or individuals

    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
    0:0.01
    1:0.14
    2:0.13
    3:0.11
    4:0.01
    5:0.02
    6:0.09
    7:0.10
    8:0.07
    9:0.07
    10:0.09
    11:0.10
    Negative Logits
    ACY
    -1.13
    ilion
    -1.04
    oria
    -1.04
    atum
    -1.03
    acy
    -1.01
    atem
    -1.00
    Mill
    -1.00
    ravity
    -0.99
    riot
    -0.99
    asse
    -0.99
    POSITIVE LOGITS
    racuse
    1.13
    Reviewer
    1.12
     Django
    1.05
     SOS
    1.04
     frogs
    1.04
     unprotected
    1.03
     democracies
    1.02
    pick
    0.99
     wart
    0.98
     commissions
    0.98
    Activations Density 0.022%

    No Known Activations