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. 7-ATT-KK
    6. 18820
    Prev
    Next
    INDEX
    Explanations

    the word "go" in contexts suggesting action or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.09
    2:0.08
    3:0.08
    4:0.07
    5:0.08
    6:0.08
    7:0.08
    8:0.07
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
    quished
    -2.35
    zan
    -2.08
    anamo
    -2.08
    scape
    -2.06
    orgetown
    -1.94
    itia
    -1.88
     Pradesh
    -1.86
     Summer
    -1.86
     moon
    -1.85
    cknow
    -1.85
    POSITIVE LOGITS
     essentially
    2.10
    グ
    2.08
     basically
    2.07
    REF
    2.02
    oval
    1.94
     contraction
    1.92
    ``
    1.92
    COMPLE
    1.92
     gimmick
    1.85
     inefficient
    1.85
    Activations Density 0.000%

    No Known Activations