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. 9357
    Prev
    Next
    INDEX
    Explanations

    quotes or dialogue within the text

    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
    0:0.07
    1:0.09
    2:0.02
    3:0.13
    4:0.14
    5:0.10
    6:0.10
    7:0.02
    8:0.04
    9:0.17
    10:0.03
    11:0.04
    Negative Logits
    ailability
    -2.19
    joice
    -2.00
    ーン
    -1.96
    oreAnd
    -1.94
    �
    -1.87
    rocal
    -1.86
    quished
    -1.85
    �
    -1.79
    byss
    -1.77
    akespe
    -1.75
    POSITIVE LOGITS
    .,"
    2.35
     adding
    2.24
     because
    1.94
     Alz
    1.91
    .""
    1.91
    _>
    1.87
    Secondly
    1.87
    ."
    1.85
    .")
    1.85
     secondly
    1.80
    Activations Density 0.042%

    No Known Activations