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. 181
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting elements

    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
    0:0.06
    1:0.07
    2:0.05
    3:0.06
    4:0.05
    5:0.06
    6:0.13
    7:0.05
    8:0.07
    9:0.04
    10:0.04
    11:0.28
    Negative Logits
    dden
    -2.79
    SPONSORED
    -2.71
    ults
    -2.68
     Corinth
    -2.64
     Corinthians
    -2.60
     Ranch
    -2.57
     Tucson
    -2.55
     Crimes
    -2.51
    00007
    -2.40
    rive
    -2.38
    POSITIVE LOGITS
     ^
    7.37
    ^^
    6.37
    ^
    6.02
     ''
    5.30
    ^^^^
    5.01
    !
    4.88
     **
    4.77
     %%
    4.44
     */
    4.37
    .*
    4.34
    Activations Density 0.000%

    No Known Activations