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. 1-ATT-KK
    6. 6354
    Prev
    Next
    INDEX
    Explanations

    expressions of personal opinions or critiques

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.1.attn.hook_z
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.11
    2:0.11
    3:0.05
    4:0.10
    5:0.04
    6:0.06
    7:0.11
    8:0.08
    9:0.06
    10:0.11
    11:0.08
    Negative Logits
     mould
    -1.28
     respectively
    -1.17
     offshore
    -1.13
     locality
    -1.11
     continental
    -1.09
    earable
    -1.09
    Available
    -1.09
    olid
    -1.08
     favourable
    -1.07
    Reloaded
    -1.07
    POSITIVE LOGITS
     rant
    1.24
    yss
    1.20
     Sons
    1.19
     texted
    1.15
    question
    1.14
     redacted
    1.13
    athe
    1.10
     Huckabee
    1.10
     Sins
    1.09
     Roose
    1.06
    Activations Density 1.291%

    No Known Activations