© 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. 9-ATT-KK
    11. 10592
    Prev
    Next
    INDEX
    Explanations

    references to television programming and production details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.11
    1:0.03
    2:0.08
    3:0.15
    4:0.07
    5:0.10
    6:0.03
    7:0.12
    8:0.10
    9:0.02
    10:0.08
    11:0.05
    Negative Logits
     �
    -2.99
    �
    -2.91
    �
    -2.87
    ··
    -2.74
    Brexit
    -2.68
    ️
    -2.67
    billion
    -2.67
     �
    -2.61
    STEP
    -2.47
    _.
    -2.42
    POSITIVE LOGITS
     narration
    2.88
     premiered
    2.66
     omitted
    2.66
     reused
    2.64
     cameo
    2.63
     composer
    2.60
    ".[
    2.56
     numbered
    2.56
     Edit
    2.53
     original
    2.53
    Activations Density 0.307%

    No Known Activations