© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 18955
    Prev
    Next
    INDEX
    Explanations

    indicative punctuation marks and special characters

    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
    0:0.02
    1:0.50
    2:0.02
    3:0.04
    4:0.04
    5:0.06
    6:0.04
    7:0.04
    8:0.02
    9:0.05
    10:0.02
    11:0.08
    Negative Logits
    iture
    -2.52
     fifty
    -2.43
     Sevent
    -2.32
     eighty
    -2.28
     sixty
    -2.26
    cise
    -2.23
    naissance
    -2.20
    iver
    -2.19
    ktop
    -2.19
     twent
    -2.16
    POSITIVE LOGITS
     3
    5.05
    3
    4.35
     2
    4.30
     4
    3.76
     third
    3.35
     Third
    3.30
    2
    3.28
    4
    2.82
    Third
    2.78
     THREE
    2.67
    Activations Density 0.086%

    No Known Activations