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. 9-ATT-KK
    6. 7577
    Prev
    Next
    INDEX
    Explanations

    references to vehicles, particularly bikes and horses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.02
    2:0.06
    3:0.19
    4:0.04
    5:0.08
    6:0.04
    7:0.05
    8:0.04
    9:0.04
    10:0.25
    11:0.02
    Negative Logits
     explanations
    -2.47
     discrepancies
    -2.32
     consequences
    -2.27
     intentions
    -2.21
    essment
    -2.20
     deficiencies
    -2.19
     refund
    -2.19
     inconsistencies
    -2.18
     alternatives
    -2.17
     refunds
    -2.15
    POSITIVE LOGITS
     subway
    2.65
     rode
    2.58
     podium
    2.48
     atop
    2.47
    atz
    2.40
     onto
    2.31
     ride
    2.27
     elevator
    2.26
     riding
    2.25
     wagon
    2.24
    Activations Density 0.006%

    No Known Activations