© 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. 10-ATT-KK
    11. 20997
    Prev
    Next
    INDEX
    Explanations

    numerical data related to approval ratings and poll percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.03
    2:0.03
    3:0.04
    4:0.07
    5:0.23
    6:0.04
    7:0.05
    8:0.02
    9:0.34
    10:0.03
    11:0.04
    Negative Logits
    owered
    -2.48
    ertodd
    -2.40
    )].
    -2.35
    acht
    -2.28
    packed
    -2.25
    culosis
    -2.22
     flooded
    -2.17
    annot
    -2.15
    staking
    -2.14
     unfocusedRange
    -2.12
    POSITIVE LOGITS
     versus
    3.68
     vs
    3.24
     according
    2.74
    %,
    2.73
     percentile
    2.73
     compared
    2.69
     deviation
    2.68
    %.
    2.66
     respectively
    2.65
    %;
    2.64
    Activations Density 0.161%

    No Known Activations