© 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. 21626
    Prev
    Next
    INDEX
    Explanations

    the presence of specific formatting or markup characters

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.06
    1:0.05
    2:0.09
    3:0.07
    4:0.08
    5:0.07
    6:0.08
    7:0.11
    8:0.07
    9:0.06
    10:0.10
    11:0.09
    Negative Logits
     Stella
    -1.69
    Aim
    -1.56
     HW
    -1.48
    Management
    -1.46
     Tenth
    -1.45
     Annex
    -1.42
    RFC
    -1.41
     conferences
    -1.40
    conference
    -1.40
    Reloaded
    -1.40
    POSITIVE LOGITS
    krit
    1.99
    akespe
    1.92
    icrobial
    1.83
    conom
    1.77
    oba
    1.76
    espie
    1.71
    atom
    1.69
    htaking
    1.65
    iotic
    1.64
     teasp
    1.62
    Activations Density 0.000%

    No Known Activations