© 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. 28555
    Prev
    Next
    INDEX
    Explanations

    references to layers in a hierarchical structure

    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
    1:0.03
    2:0.08
    3:0.08
    4:0.13
    5:0.02
    6:0.06
    7:0.28
    8:0.02
    9:0.03
    10:0.04
    11:0.17
    Negative Logits
    Percent
    -1.79
    ′
    -1.52
    626
    -1.47
    pport
    -1.46
     Response
    -1.43
    875
    -1.42
    CVE
    -1.39
    density
    -1.39
    PD
    -1.38
    pez
    -1.36
    POSITIVE LOGITS
     premises
    1.55
     speculation
    1.52
     undercover
    1.38
     Strauss
    1.36
     keyboards
    1.35
     guise
    1.34
     fray
    1.30
     loopholes
    1.30
     BAS
    1.30
     murky
    1.30
    Activations Density 0.000%

    No Known Activations