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. 18883
    Prev
    Next
    INDEX
    Explanations

    requirements and conditions related to organizations and infrastructures

    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
    0:0.04
    1:0.06
    2:0.02
    3:0.06
    4:0.06
    5:0.25
    6:0.08
    7:0.14
    8:0.05
    9:0.05
    10:0.04
    11:0.09
    Negative Logits
    trak
    -2.31
     interchange
    -2.13
     cavalry
    -2.10
     Toledo
    -2.01
     quar
    -2.01
     Caldwell
    -1.98
     helic
    -1.98
     Wik
    -1.97
    yne
    -1.96
    alion
    -1.95
    POSITIVE LOGITS
    worthiness
    3.05
    Accept
    2.72
    reasonable
    2.59
    iqueness
    2.54
    orthy
    2.50
    acceptable
    2.43
    reason
    2.41
    olerance
    2.40
    Limit
    2.36
     sufficiently
    2.36
    Activations Density 0.009%

    No Known Activations