© 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. 9-ATT-KK
    11. 4677
    Prev
    Next
    INDEX
    Explanations

    references to deception or misinformation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.02
    2:0.05
    3:0.22
    4:0.01
    5:0.05
    6:0.02
    7:0.04
    8:0.02
    9:0.03
    10:0.44
    11:0.02
    Negative Logits
    ersed
    -2.09
    igsaw
    -1.83
    Narr
    -1.81
    ominium
    -1.80
     recounts
    -1.80
    roxy
    -1.80
    choes
    -1.76
     Airl
    -1.76
    ��
    -1.75
     dissect
    -1.73
    POSITIVE LOGITS
     unworthy
    3.36
     unsu
    3.19
     unfit
    3.18
     worthy
    3.16
    worthy
    2.95
     weakest
    2.58
    worthiness
    2.51
     preferable
    2.48
     deserving
    2.48
     suitable
    2.47
    Activations Density 0.211%

    No Known Activations