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. 10-ATT-KK
    6. 14758
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms or concepts related to technology and engineering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.20
    1:0.13
    2:0.06
    3:0.06
    4:0.05
    5:0.03
    6:0.07
    7:0.08
    8:0.03
    9:0.04
    10:0.14
    11:0.06
    Negative Logits
    ortmund
    -3.35
    SpaceEngineers
    -3.12
    zi
    -3.02
    ettlement
    -3.00
     Zhang
    -2.97
     WARN
    -2.95
    BuyableInstoreAndOnline
    -2.94
     Bears
    -2.94
    ledged
    -2.84
     Rw
    -2.83
    POSITIVE LOGITS
     Electro
    9.49
     electro
    7.04
     electroly
    5.49
    Elect
    5.49
    elect
    4.80
     Elect
    4.76
     electrode
    4.54
    Electric
    4.53
     ELECT
    4.42
     Electric
    4.40
    Activations Density 0.001%

    No Known Activations