© 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. 5-ATT-KK
    11. 41396
    Prev
    Next
    INDEX
    Explanations

    the infinitive form of verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.02
    2:0.14
    3:0.08
    4:0.10
    5:0.02
    6:0.11
    7:0.23
    8:0.03
    9:0.03
    10:0.06
    11:0.11
    Negative Logits
    iety
    -1.55
     piety
    -1.48
    ensual
    -1.46
     gravy
    -1.45
     Voy
    -1.43
     Wonderful
    -1.36
    anced
    -1.33
     Proced
    -1.33
     intrinsic
    -1.31
    ient
    -1.31
    POSITIVE LOGITS
    keye
    1.60
    anus
    1.57
    hin
    1.44
    ANN
    1.43
     warn
    1.42
    esson
    1.41
    LIN
    1.37
    igers
    1.37
    hello
    1.36
     batters
    1.34
    Activations Density 0.001%

    No Known Activations