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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 16618
    Prev
    Next
    INDEX
    Explanations

    discussions around costs, prices, and financial implications

    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
    0:0.10
    1:0.02
    2:0.40
    3:0.12
    4:0.03
    5:0.09
    6:0.03
    7:0.04
    8:0.02
    9:0.04
    10:0.05
    11:0.01
    Negative Logits
     Survivors
    -2.54
    ija
    -2.44
    ythm
    -2.41
     Hug
    -2.41
    dit
    -2.38
    inct
    -2.34
    letes
    -2.32
     prophetic
    -2.31
     delet
    -2.19
    iasm
    -2.17
    POSITIVE LOGITS
     pricing
    6.24
     price
    6.24
     prices
    6.05
     cost
    5.95
     costs
    5.79
     cheapest
    5.78
     pric
    5.76
     priced
    5.65
     cheaper
    5.64
    price
    5.53
    Activations Density 1.410%

    No Known Activations