© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 28324
    Prev
    Next
    INDEX
    Explanations

    terms associated with dominance or prevalence in various contexts

    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
    0:0.01
    1:0.02
    2:0.05
    3:0.05
    4:0.26
    5:0.02
    6:0.03
    7:0.31
    8:0.02
    9:0.02
    10:0.05
    11:0.09
    Negative Logits
     reconnect
    -1.79
    awaru
    -1.71
     defect
    -1.70
     condol
    -1.59
    intent
    -1.56
    cised
    -1.54
     disconnect
    -1.53
    ortium
    -1.50
    rentices
    -1.48
     intention
    -1.47
    POSITIVE LOGITS
     corridors
    1.45
     halls
    1.45
    waves
    1.42
    @@@@
    1.40
     margins
    1.38
     Brill
    1.35
     ranks
    1.34
     Cups
    1.34
     throne
    1.33
    hill
    1.33
    Activations Density 0.010%

    No Known Activations