Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9122
    Prev
    Next
    INDEX
    Explanations

    terms related to the demilitarized zone and its characteristics

    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
    0:0.16
    1:0.04
    2:0.03
    3:0.05
    4:0.03
    5:0.08
    6:0.05
    7:0.02
    8:0.43
    9:0.04
    10:0.02
    11:0.02
    Negative Logits
     nightmares
    -1.62
    AUD
    -1.59
    untu
    -1.54
    nz
    -1.50
    iov
    -1.46
     weddings
    -1.45
    Fax
    -1.44
    tis
    -1.43
    Reviewer
    -1.42
     Oral
    -1.42
    POSITIVE LOGITS
     disbanded
    1.70
    hene
    1.68
     disband
    1.66
     separ
    1.63
     empty
    1.63
     bridges
    1.59
     separating
    1.54
    framework
    1.53
     trenches
    1.53
     horizont
    1.52
    Activations Density 0.000%

    No Known Activations