© 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. 6460
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate actions or states related to potential consequences or results

    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
    1:0.06
    2:0.06
    3:0.04
    4:0.02
    5:0.03
    6:0.05
    7:0.04
    8:0.08
    9:0.41
    10:0.07
    11:0.08
    Negative Logits
     cent
    -1.37
    teness
    -1.27
     Sins
    -1.22
    icion
    -1.20
    bill
    -1.19
    lies
    -1.14
    vs
    -1.13
     Medals
    -1.11
    enegger
    -1.10
    tons
    -1.09
    POSITIVE LOGITS
     safely
    1.55
     freely
    1.54
     flourish
    1.49
    rehend
    1.47
     forcefully
    1.44
     suffice
    1.43
     calmly
    1.40
     peacefully
    1.38
     succeed
    1.37
     negotiate
    1.36
    Activations Density 0.057%

    No Known Activations