© 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. 43102
    Prev
    Next
    INDEX
    Explanations

    various forms of the verb "to be" and nominalizations derived from verbs

    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
    1:0.14
    2:0.05
    3:0.07
    4:0.03
    5:0.12
    6:0.08
    7:0.03
    8:0.11
    9:0.06
    10:0.07
    11:0.06
    Negative Logits
     Bentley
    -1.63
     Shirley
    -1.51
     Avery
    -1.49
     Ronnie
    -1.48
     Had
    -1.46
     Redmond
    -1.43
     Kore
    -1.43
     living
    -1.43
    odore
    -1.43
     Jarrett
    -1.42
    POSITIVE LOGITS
     expires
    1.98
    ocument
    1.78
    actionDate
    1.76
    taboola
    1.74
    merce
    1.66
    odes
    1.64
     acknow
    1.64
     pdf
    1.61
    ratulations
    1.61
    ufact
    1.60
    Activations Density 0.000%

    No Known Activations