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. 9278
    Prev
    Next
    INDEX
    Explanations

    mentions of statistical data related to sports performance

    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
    0:0.05
    1:0.08
    2:0.05
    3:0.06
    4:0.09
    5:0.05
    6:0.06
    7:0.22
    8:0.08
    9:0.08
    10:0.05
    11:0.07
    Negative Logits
     神
    -2.16
    heid
    -2.14
     fluor
    -2.08
     racists
    -2.04
     fascists
    -1.97
     ner
    -1.97
     Zig
    -1.96
     liberals
    -1.94
     sexist
    -1.90
    UP
    -1.89
    POSITIVE LOGITS
     outings
    2.37
    isodes
    2.31
     weekly
    2.22
    sequently
    2.16
    regular
    2.10
    illet
    2.08
    aleb
    2.07
     voyage
    2.04
    ournals
    2.03
     monthly
    2.03
    Activations Density 0.000%

    No Known Activations