© 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. 2-ATT-KK
    11. 14288
    Prev
    Next
    INDEX
    Explanations

    phrases related to falsification and manipulation of data

    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
    1:0.03
    2:0.21
    3:0.09
    4:0.20
    5:0.05
    6:0.03
    7:0.03
    8:0.06
    9:0.12
    10:0.05
    11:0.03
    Negative Logits
    imar
    -1.53
    joy
    -1.45
     Sabha
    -1.44
    ��
    -1.39
     Neh
    -1.33
     mosqu
    -1.33
     Ribbon
    -1.25
    bats
    -1.23
     helicop
    -1.18
    enment
    -1.18
    POSITIVE LOGITS
     omission
    1.77
     hoax
    1.44
     fals
    1.36
     misrepresent
    1.27
     irregularities
    1.24
     deception
    1.23
     fraud
    1.22
     nonexistent
    1.21
     Wrong
    1.21
     instrumental
    1.19
    Activations Density 0.001%

    No Known Activations