© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 46888
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate conditional situations or reasons for outcomes

    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
    0:0.03
    1:0.02
    2:0.44
    3:0.08
    4:0.08
    5:0.04
    6:0.05
    7:0.04
    8:0.05
    9:0.03
    10:0.05
    11:0.04
    Negative Logits
    �
    -1.67
    yles
    -1.54
    vale
    -1.49
    Recipe
    -1.47
    hammad
    -1.42
    forts
    -1.42
    legram
    -1.41
    hower
    -1.41
     Nau
    -1.40
    Cause
    -1.37
    POSITIVE LOGITS
    entious
    1.32
     medically
    1.28
     Grade
    1.28
     mature
    1.26
    umatic
    1.25
    atched
    1.25
    eligible
    1.24
     leap
    1.24
     undecided
    1.23
    ueless
    1.23
    Activations Density 0.125%

    No Known Activations