© 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. 21239
    Prev
    Next
    INDEX
    Explanations

    phrases related to unexpected results and proposals

    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
    1:0.03
    2:0.04
    3:0.24
    4:0.02
    5:0.08
    6:0.02
    7:0.05
    8:0.02
    9:0.02
    10:0.36
    11:0.01
    Negative Logits
     graz
    -2.15
     visited
    -1.99
     closely
    -1.80
     participating
    -1.77
     brunt
    -1.77
     witness
    -1.76
     intimately
    -1.76
     watching
    -1.76
     attending
    -1.75
     nurt
    -1.71
    POSITIVE LOGITS
     justification
    2.42
     gimmick
    2.33
     excuses
    2.31
     rationale
    2.22
    ensible
    2.19
     catchy
    2.15
     nifty
    2.13
     excuse
    2.12
     ridiculous
    2.04
     ingenious
    2.02
    Activations Density 0.078%

    No Known Activations