Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 7682
    Prev
    Next
    INDEX
    Explanations

    phrases indicating pretense or impersonation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.04
    2:0.07
    3:0.14
    4:0.02
    5:0.03
    6:0.04
    7:0.07
    8:0.08
    9:0.22
    10:0.06
    11:0.14
    Negative Logits
    ilst
    -2.22
    requires
    -1.35
    ourses
    -1.23
    sections
    -1.20
    ichever
    -1.16
    arger
    -1.15
    ests
    -1.14
    hens
    -1.14
    Detailed
    -1.12
    alon
    -1.11
    POSITIVE LOGITS
     nostalg
    1.36
     Clown
    1.22
     imitation
    1.20
    false
    1.18
     pretend
    1.15
     innocence
    1.14
     Duck
    1.13
     Godd
    1.11
     pretended
    1.10
     cav
    1.09
    Activations Density 0.014%

    No Known Activations