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. 9050
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals related to news events

    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
    0:0.06
    1:0.07
    2:0.32
    3:0.05
    4:0.04
    5:0.05
    6:0.05
    7:0.04
    8:0.04
    9:0.05
    10:0.11
    11:0.05
    Negative Logits
    LEASE
    -2.60
    REDACTED
    -2.45
    EStreamFrame
    -2.44
    NER
    -2.39
    LOS
    -2.34
    nai
    -2.27
    externalActionCode
    -2.23
     "_
    -2.22
    ال
    -2.14
    2018
    -2.09
    POSITIVE LOGITS
    ich
    3.08
     strut
    2.58
     Ich
    2.48
    uch
    2.47
     Mach
    2.34
     hawk
    2.28
    avid
    2.27
     mach
    2.25
     bout
    2.24
    vich
    2.22
    Activations Density 0.000%

    No Known Activations