© 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. 45743
    Prev
    Next
    INDEX
    Explanations

    mentions of investment, financial goals, and potential improvements 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
    0:0.06
    1:0.02
    2:0.11
    3:0.09
    4:0.41
    5:0.02
    6:0.06
    7:0.03
    8:0.04
    9:0.03
    10:0.04
    11:0.03
    Negative Logits
    arel
    -2.15
    ibrary
    -1.83
    obyl
    -1.48
    acio
    -1.44
     Rubin
    -1.42
    ás
    -1.42
    igm
    -1.40
    gomery
    -1.39
     Discuss
    -1.34
    igmatic
    -1.33
    POSITIVE LOGITS
     sucked
    1.66
     dont
    1.50
    ready
    1.50
     doesnt
    1.49
     substituted
    1.45
     didnt
    1.45
     wont
    1.44
     silence
    1.43
     replaced
    1.40
     sucks
    1.39
    Activations Density 0.560%

    No Known Activations