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. 9-ATT-KK
    6. 3039
    Prev
    Next
    INDEX
    Explanations

    important details and validations in news reports or articles

    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
    0:0.08
    1:0.02
    2:0.06
    3:0.03
    4:0.05
    5:0.04
    6:0.26
    7:0.04
    8:0.08
    9:0.23
    10:0.02
    11:0.04
    Negative Logits
     ACS
    -3.84
    sword
    -3.80
    à
    -3.68
     Sai
    -3.60
    ousse
    -3.50
     Piano
    -3.46
    Sword
    -3.43
    onse
    -3.41
    Nap
    -3.40
     Angola
    -3.36
    POSITIVE LOGITS
     Kel
    9.82
     Kelley
    9.22
     Kelvin
    5.13
    kel
    5.10
     Keller
    4.85
     Kinder
    4.84
     Kell
    4.66
     Gul
    4.58
     Kelly
    4.41
     ke
    4.39
    Activations Density 0.002%

    No Known Activations