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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 44387
    Prev
    Next
    INDEX
    Explanations

    instances where honesty or truthfulness is expressed

    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
    1:0.01
    2:0.10
    3:0.10
    4:0.18
    5:0.03
    6:0.04
    7:0.23
    8:0.04
    9:0.02
    10:0.05
    11:0.12
    Negative Logits
    ificantly
    -1.56
    ander
    -1.56
    =-=-=-=-=-=-=-=-
    -1.52
    alyst
    -1.49
    orses
    -1.47
    ritch
    -1.46
    erity
    -1.46
    ullivan
    -1.45
    anders
    -1.44
    frey
    -1.38
    POSITIVE LOGITS
     encl
    1.22
     collateral
    1.19
    ctors
    1.19
     delim
    1.18
     Sessions
    1.17
     [|
    1.17
     Congress
    1.16
     Ging
    1.15
     suppose
    1.14
     Scand
    1.12
    Activations Density 0.001%

    No Known Activations