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. 3-ATT-KK
    6. 8532
    Prev
    Next
    INDEX
    Explanations

    references to action or cause, particularly concerning how something is driven or influenced

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.03
    2:0.07
    3:0.28
    4:0.02
    5:0.04
    6:0.05
    7:0.07
    8:0.06
    9:0.12
    10:0.09
    11:0.09
    Negative Logits
    ital
    -1.52
    mint
    -1.48
    isha
    -1.41
    ipped
    -1.31
    bilt
    -1.26
    FACE
    -1.25
    KO
    -1.23
    nai
    -1.23
    vati
    -1.23
    INGTON
    -1.23
    POSITIVE LOGITS
     pandemonium
    1.25
    runner
    1.25
     glyc
    1.25
     totality
    1.21
     repression
    1.21
     regeneration
    1.20
     inflation
    1.18
     improvement
    1.16
     innovation
    1.15
     weaving
    1.14
    Activations Density 0.009%

    No Known Activations