© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 35867
    Prev
    Next
    INDEX
    Explanations

    references to payment and financial recommendations

    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
    1:0.05
    2:0.07
    3:0.19
    4:0.14
    5:0.06
    6:0.04
    7:0.04
    8:0.05
    9:0.06
    10:0.07
    11:0.14
    Negative Logits
     precip
    -1.40
     cavity
    -1.38
     expelled
    -1.38
     …"
    -1.34
    upon
    -1.33
    sic
    -1.30
     emptied
    -1.29
     griev
    -1.27
     pits
    -1.26
     stricken
    -1.25
    POSITIVE LOGITS
    eff
    1.43
    inventoryQuantity
    1.40
    yrights
    1.36
    Paper
    1.33
    erie
    1.33
    Writer
    1.32
    amins
    1.31
     Designs
    1.30
    eworks
    1.29
    lation
    1.29
    Activations Density 0.000%

    No Known Activations