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. 5-ATT-KK
    6. 44151
    Prev
    Next
    INDEX
    Explanations

    first-person and plural pronouns indicating personal perspectives and involvement

    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
    0:0.06
    1:0.04
    2:0.05
    3:0.06
    4:0.05
    5:0.11
    6:0.04
    7:0.02
    8:0.31
    9:0.06
    10:0.10
    11:0.05
    Negative Logits
     leng
    -1.91
     paste
    -1.74
     clips
    -1.72
    MpServer
    -1.66
     suffice
    -1.66
    impact
    -1.65
     contained
    -1.63
     expires
    -1.61
     contains
    -1.59
     resur
    -1.58
    POSITIVE LOGITS
    romy
    1.80
    yssey
    1.74
     dearly
    1.70
    gow
    1.64
     sophistic
    1.63
    brance
    1.60
    atalie
    1.59
     Secondary
    1.59
    ithmetic
    1.58
    lia
    1.58
    Activations Density 0.004%

    No Known Activations