© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 15434
    Prev
    Next
    INDEX
    Explanations

    conjunctions and distinctions in sentences

    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
    1:0.07
    2:0.08
    3:0.09
    4:0.10
    5:0.06
    6:0.06
    7:0.09
    8:0.07
    9:0.08
    10:0.07
    11:0.09
    Negative Logits
    >]
    -2.81
    course
    -2.66
    itar
    -2.62
     <-
    -2.61
    ourses
    -2.59
    agin
    -2.58
    species
    -2.54
    }:
    -2.52
    philis
    -2.52
    inctions
    -2.51
    POSITIVE LOGITS
     Craig
    2.95
    Craig
    2.67
     Webb
    2.57
     Gareth
    2.57
     Terry
    2.56
    ItemTracker
    2.50
     Werner
    2.46
     Baird
    2.44
    Andy
    2.42
     Heather
    2.41
    Activations Density 0.000%

    No Known Activations