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. 166
    Prev
    Next
    INDEX
    Explanations

    specific references to the Quran in the context of education or assessment

    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
    0:0.07
    1:0.09
    2:0.07
    3:0.08
    4:0.07
    5:0.08
    6:0.09
    7:0.07
    8:0.08
    9:0.09
    10:0.08
    11:0.07
    Negative Logits
     Apps
    -3.07
     Bot
    -2.86
     Brew
    -2.82
    orks
    -2.78
     Recipes
    -2.74
     Simulator
    -2.68
     Bott
    -2.67
     mashed
    -2.59
     Sci
    -2.52
     gimm
    -2.50
    POSITIVE LOGITS
    bilt
    3.09
     Daesh
    2.82
     Zhou
    2.72
    261
    2.60
    ONY
    2.56
    551
    2.56
    194
    2.53
    656
    2.52
    phis
    2.50
    Pont
    2.50
    Activations Density 0.000%

    No Known Activations