© 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. 43301
    Prev
    Next
    INDEX
    Explanations

    negative or critical sentiments regarding technology or products

    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
    0:0.03
    1:0.02
    2:0.08
    3:0.08
    4:0.15
    5:0.05
    6:0.21
    7:0.05
    8:0.06
    9:0.06
    10:0.09
    11:0.07
    Negative Logits
    SEE
    -1.37
     whoever
    -1.27
     plotting
    -1.25
     cheating
    -1.24
     staying
    -1.23
     dying
    -1.23
     dreaming
    -1.23
     passing
    -1.21
     planning
    -1.21
     steering
    -1.20
    POSITIVE LOGITS
     corrid
    1.58
    agonist
    1.41
    ゴン
    1.39
    ocally
    1.39
    dimension
    1.37
    eteenth
    1.36
    imes
    1.34
    orned
    1.30
    enged
    1.25
    etimes
    1.25
    Activations Density 0.001%

    No Known Activations