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. 9378
    Prev
    Next
    INDEX
    Explanations

    social media links and references to online content

    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
    0:0.10
    1:0.04
    2:0.01
    3:0.10
    4:0.19
    5:0.12
    6:0.04
    7:0.03
    8:0.20
    9:0.06
    10:0.03
    11:0.02
    Negative Logits
    :-
    -2.08
    :\
    -2.03
    naire
    -1.91
     broch
    -1.89
    cape
    -1.87
    :(
    -1.86
    anche
    -1.84
    abouts
    -1.78
    istan
    -1.76
    gor
    -1.73
    POSITIVE LOGITS
    ッド
    1.87
    METHOD
    1.75
     hobbies
    1.73
    uncture
    1.71
     antagonists
    1.70
     celeb
    1.65
     Notting
    1.65
     teasp
    1.64
    politics
    1.59
    umenthal
    1.58
    Activations Density 0.002%

    No Known Activations