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. 18944
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases indicating a state of being or response

    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
    0:0.05
    1:0.03
    2:0.01
    3:0.12
    4:0.13
    5:0.05
    6:0.07
    7:0.02
    8:0.35
    9:0.07
    10:0.02
    11:0.02
    Negative Logits
     Parish
    -1.76
     himself
    -1.71
     pen
    -1.67
     devote
    -1.63
    agall
    -1.63
     die
    -1.60
     myself
    -1.59
     Journals
    -1.58
     Himself
    -1.57
     careers
    -1.56
    POSITIVE LOGITS
    escal
    2.09
    Looks
    1.85
    avia
    1.75
     reflects
    1.71
    Shock
    1.70
    00200000
    1.70
     000000
    1.68
    Against
    1.68
    FACE
    1.66
     mirrors
    1.65
    Activations Density 0.010%

    No Known Activations