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. 18946
    Prev
    Next
    INDEX
    Explanations

    actions or processes related to production, repair, and maintenance in various contexts

    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
    0:0.11
    1:0.04
    2:0.01
    3:0.20
    4:0.14
    5:0.16
    6:0.04
    7:0.03
    8:0.07
    9:0.12
    10:0.01
    11:0.01
    Negative Logits
    �醒
    -2.21
    anian
    -2.12
     suspic
    -2.03
     slippery
    -2.00
    arij
    -1.98
    aturday
    -1.95
     bashing
    -1.94
     blaming
    -1.94
     predic
    -1.94
    ancial
    -1.93
    POSITIVE LOGITS
    yle
    2.33
    rb
    1.97
    LR
    1.96
    /,
    1.91
     Wyoming
    1.88
    SG
    1.87
    });
    1.85
    ovych
    1.84
     translate
    1.81
    }:
    1.80
    Activations Density 0.017%

    No Known Activations