© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 6497
    Prev
    Next
    INDEX
    Explanations

    rhetorical questions throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.05
    2:0.06
    3:0.02
    4:0.06
    5:0.11
    6:0.14
    7:0.06
    8:0.06
    9:0.16
    10:0.09
    11:0.12
    Negative Logits
     disag
    -1.33
    isc
    -1.24
    fter
    -1.20
     controvers
    -1.12
    responsive
    -1.11
     fruitful
    -1.11
     respectively
    -1.11
     forthcoming
    -1.10
     racially
    -1.08
    imates
    -1.07
    POSITIVE LOGITS
     yourself
    1.45
    your
    1.35
     Floyd
    1.30
     yourselves
    1.27
     ain
    1.24
    Your
    1.23
     your
    1.21
     WARRANT
    1.18
     gotta
    1.16
    anamo
    1.13
    Activations Density 0.153%

    No Known Activations