© 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. 2-ATT-KK
    11. 14145
    Prev
    Next
    INDEX
    Explanations

    words related to hindering or preventing something

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.02
    2:0.08
    3:0.05
    4:0.34
    5:0.04
    6:0.03
    7:0.02
    8:0.18
    9:0.06
    10:0.04
    11:0.02
    Negative Logits
     ILCS
    -1.63
     Forbes
    -1.45
     adjusted
    -1.43
    �
    -1.40
    shire
    -1.40
    eport
    -1.38
    adder
    -1.36
     Shutterstock
    -1.34
    terday
    -1.33
    raq
    -1.28
    POSITIVE LOGITS
     Cruel
    1.42
     unnecessary
    1.42
     bothering
    1.41
     compl
    1.38
     boredom
    1.36
     tampering
    1.35
     overly
    1.30
     debilitating
    1.28
     waiting
    1.24
     deliberate
    1.24
    Activations Density 0.004%

    No Known Activations