© 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. 37219
    Prev
    Next
    INDEX
    Explanations

    questions and words related to evaluating situations or issues

    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
    0:0.01
    1:0.00
    2:0.15
    3:0.12
    4:0.31
    5:0.03
    6:0.11
    7:0.06
    8:0.03
    9:0.03
    10:0.05
    11:0.04
    Negative Logits
    ournal
    -1.59
    DERR
    -1.30
    erity
    -1.23
    ceive
    -1.23
     slate
    -1.22
    undreds
    -1.20
    eca
    -1.19
     portions
    -1.19
    iage
    -1.18
    orc
    -1.17
    POSITIVE LOGITS
    isible
    1.57
    Marx
    1.47
    starter
    1.45
     coincidence
    1.41
    )?
    1.39
    …)
    1.34
    omatic
    1.31
    Huh
    1.29
    Gun
    1.29
    .):
    1.22
    Activations Density 0.010%

    No Known Activations