© 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. 33595
    Prev
    Next
    INDEX
    Explanations

    phrases indicating measurements of performance or evaluation metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    2:0.12
    3:0.07
    4:0.14
    5:0.03
    6:0.04
    7:0.25
    8:0.04
    9:0.03
    10:0.09
    11:0.09
    Negative Logits
    zinski
    -2.09
    soType
    -1.68
     Deaths
    -1.65
     Consent
    -1.64
    ISTORY
    -1.60
    姫
    -1.54
    vation
    -1.50
    igun
    -1.50
    ♦
    -1.49
    ="#
    -1.47
    POSITIVE LOGITS
     lapt
    1.53
     centrif
    1.48
     throughput
    1.46
     algorithms
    1.40
     hurd
    1.40
     subsystem
    1.40
     comprom
    1.38
     cryptographic
    1.38
     synthes
    1.36
     incumb
    1.31
    Activations Density 0.001%

    No Known Activations