© 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. 40489
    Prev
    Next
    INDEX
    Explanations

    references to parliamentary members and their standings in various contexts

    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
    0:0.13
    1:0.19
    2:0.04
    3:0.05
    4:0.04
    5:0.23
    6:0.04
    7:0.02
    8:0.07
    9:0.05
    10:0.05
    11:0.03
    Negative Logits
     marches
    -1.82
    accompan
    -1.64
     horizont
    -1.59
     GOODMAN
    -1.58
     bends
    -1.56
     Ori
    -1.55
     Ess
    -1.54
     Bend
    -1.52
     Orient
    -1.51
     Maid
    -1.50
    POSITIVE LOGITS
    bill
    2.48
    jit
    2.17
    xc
    2.12
    num
    2.10
    fx
    2.10
    p
    2.06
    mu
    2.05
    gc
    2.04
    tmp
    2.00
    x
    2.00
    Activations Density 0.003%

    No Known Activations