© 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. 14290
    Prev
    Next
    INDEX
    Explanations

    phrases related to resets or starting over

    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
    0:0.06
    1:0.07
    2:0.18
    3:0.06
    4:0.07
    5:0.06
    6:0.03
    7:0.03
    8:0.17
    9:0.15
    10:0.06
    11:0.03
    Negative Logits
    omorphic
    -1.39
    stood
    -1.38
    osher
    -1.34
    و
    -1.33
    erved
    -1.33
    ingly
    -1.29
    phot
    -1.29
     mortg
    -1.28
    bleacher
    -1.27
    是
    -1.26
    POSITIVE LOGITS
     timer
    1.59
     cooldown
    1.51
     Delete
    1.45
     Stage
    1.38
     Centauri
    1.38
     Deadline
    1.37
     valve
    1.32
     Desktop
    1.32
     Sequence
    1.31
    Stage
    1.31
    Activations Density 0.009%

    No Known Activations