© 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. 3-ATT-KK
    11. 9505
    Prev
    Next
    INDEX
    Explanations

    phrases related to consequences and rewards

    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
    0:0.02
    1:0.04
    2:0.10
    3:0.03
    4:0.01
    5:0.03
    6:0.09
    7:0.34
    8:0.09
    9:0.02
    10:0.14
    11:0.04
    Negative Logits
    staking
    -1.07
    Movie
    -0.98
     PIN
    -0.96
     KE
    -0.95
    mad
    -0.92
    conf
    -0.91
    abase
    -0.91
    PIN
    -0.91
     Pwr
    -0.91
    ickr
    -0.90
    POSITIVE LOGITS
     respectively
    1.38
     accord
    1.28
    kens
    1.11
    airs
    1.09
    aeper
    1.01
    ectar
    1.01
    este
    1.01
    aepernick
    1.00
    eties
    0.98
    glers
    0.98
    Activations Density 1.711%

    No Known Activations