© 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. 43112
    Prev
    Next
    INDEX
    Explanations

    instances of numerical lists or enumerated items

    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
    0:0.14
    1:0.08
    2:0.10
    3:0.04
    4:0.04
    5:0.11
    6:0.03
    7:0.02
    8:0.09
    9:0.09
    10:0.05
    11:0.15
    Negative Logits
    Args
    -1.59
    ADRA
    -1.58
    amo
    -1.50
    behind
    -1.46
    zai
    -1.44
    Bus
    -1.41
    )|
    -1.41
    BBC
    -1.40
    remlin
    -1.40
     Roose
    -1.40
    POSITIVE LOGITS
    ttle
    1.53
     Intermediate
    1.53
     jurisdiction
    1.40
     regulated
    1.34
     principally
    1.31
     licensing
    1.29
     professionally
    1.28
     trad
    1.28
    iencies
    1.27
     discretion
    1.25
    Activations Density 0.004%

    No Known Activations