© 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. 1397
    Prev
    Next
    INDEX
    Explanations

    cohesive conjunctions, particularly the word "and" in various contexts

    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
    1:0.34
    2:0.04
    3:0.11
    4:0.03
    5:0.09
    6:0.06
    7:0.08
    8:0.04
    9:0.02
    10:0.03
    11:0.04
    Negative Logits
    Certain
    -2.89
     1840
    -2.85
    IV
    -2.81
    INT
    -2.75
    ACH
    -2.71
    ween
    -2.65
     Certain
    -2.61
    current
    -2.58
     Barth
    -2.56
    anyl
    -2.54
    POSITIVE LOGITS
     NASL
    2.72
    ichick
    2.68
    nings
    2.62
    son
    2.60
    rup
    2.53
    seys
    2.53
    ttp
    2.53
    ordan
    2.50
    rament
    2.47
    pez
    2.41
    Activations Density 0.002%

    No Known Activations