© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 19660
    Prev
    Next
    INDEX
    Explanations

    references to the FBI and its investigations, particularly regarding its actions and the implications of those actions in high-profile cases

    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
    0:0.23
    1:0.01
    2:0.18
    3:0.08
    4:0.04
    5:0.11
    6:0.03
    7:0.06
    8:0.13
    9:0.03
    10:0.02
    11:0.01
    Negative Logits
     Rugby
    -2.83
     rugby
    -2.78
    obyl
    -2.52
     apologised
    -2.50
     GSL
    -2.46
     councillors
    -2.43
     skating
    -2.40
     apologise
    -2.40
    �
    -2.38
    cream
    -2.38
    POSITIVE LOGITS
    FBI
    5.77
     FBI
    5.46
     ATF
    4.16
     Comey
    3.80
     McCabe
    3.75
     informant
    3.73
     detectives
    3.43
     bureau
    3.42
     investigators
    3.38
     Abedin
    3.37
    Activations Density 0.122%

    No Known Activations