© 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. 36424
    Prev
    Next
    INDEX
    Explanations

    significant numerical values and tangible descriptors related to plans and endeavors

    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
    0:0.02
    1:0.02
    2:0.16
    3:0.09
    4:0.11
    5:0.03
    6:0.26
    7:0.10
    8:0.03
    9:0.02
    10:0.06
    11:0.04
    Negative Logits
    haps
    -1.75
    abwe
    -1.48
    ��
    -1.43
    ovi
    -1.43
    egu
    -1.43
    olor
    -1.41
    aba
    -1.40
    withstanding
    -1.38
    aline
    -1.35
     srf
    -1.33
    POSITIVE LOGITS
    sheets
    1.32
     Gross
    1.30
    hearted
    1.26
     phases
    1.22
     HAS
    1.21
    physical
    1.21
     revolves
    1.21
     Including
    1.20
    blood
    1.18
    aways
    1.18
    Activations Density 0.023%

    No Known Activations