© 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. 12856
    Prev
    Next
    INDEX
    Explanations

    expressions of evaluation or commentary, particularly those indicating a degree of significance or relevance

    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
    0:0.04
    1:0.03
    2:0.06
    3:0.13
    4:0.03
    5:0.08
    6:0.03
    7:0.07
    8:0.03
    9:0.03
    10:0.40
    11:0.03
    Negative Logits
     Elliott
    -1.93
     contribut
    -1.89
     tropes
    -1.88
     canon
    -1.77
     Acts
    -1.73
     mobs
    -1.71
     liable
    -1.71
     pending
    -1.69
    arnaev
    -1.66
     Painter
    -1.65
    POSITIVE LOGITS
    hest
    2.38
    )</
    2.33
    ropy
    2.24
     least
    2.20
    ighter
    2.16
    saf
    2.12
    EST
    2.10
    arest
    2.05
    ministic
    2.03
    naissance
    1.97
    Activations Density 0.001%

    No Known Activations