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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19344
    Prev
    Next
    INDEX
    Explanations

    prepositions and phrases indicating direction or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.01
    1:0.01
    2:0.04
    3:0.04
    4:0.10
    5:0.02
    6:0.09
    7:0.34
    8:0.03
    9:0.03
    10:0.10
    11:0.12
    Negative Logits
     Factor
    -1.41
     GOODMAN
    -1.38
     Tale
    -1.34
     weeds
    -1.32
     Indigo
    -1.31
     Towns
    -1.31
     Conv
    -1.30
     Transcript
    -1.29
     Fever
    -1.28
     Deaths
    -1.27
    POSITIVE LOGITS
    eca
    1.50
    interstitial
    1.39
    iosyn
    1.37
    leasing
    1.37
    ranch
    1.35
     maximizing
    1.35
    esa
    1.35
     aiming
    1.33
     squarely
    1.33
    ット
    1.30
    Activations Density 0.012%

    No Known Activations