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. 2-ATT-KK
    6. 14029
    Prev
    Next
    INDEX
    Explanations

    phrases containing possessive pronouns

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.01
    2:0.20
    3:0.17
    4:0.25
    5:0.06
    6:0.02
    7:0.01
    8:0.04
    9:0.07
    10:0.04
    11:0.02
    Negative Logits
     Boo
    -1.37
     morale
    -1.29
     Lv
    -1.28
     Scar
    -1.28
     Capt
    -1.26
     Pars
    -1.25
     Fleming
    -1.24
     Purch
    -1.23
     Dow
    -1.22
    Ship
    -1.18
    POSITIVE LOGITS
    emonic
    1.86
    sonian
    1.76
    azeera
    1.67
    acea
    1.62
    idge
    1.61
    icka
    1.58
    fork
    1.54
    itans
    1.47
    itle
    1.44
    isphere
    1.40
    Activations Density 0.066%

    No Known Activations