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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 7697
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and demographics in relation to notable events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.01
    2:0.25
    3:0.20
    4:0.13
    5:0.01
    6:0.02
    7:0.07
    8:0.07
    9:0.04
    10:0.08
    11:0.06
    Negative Logits
    pite
    -1.56
    emort
    -1.52
    rompt
    -1.50
    channelAvailability
    -1.44
    wordpress
    -1.33
    ebin
    -1.29
    erity
    -1.28
    cause
    -1.28
     nodd
    -1.25
     Pastebin
    -1.23
    POSITIVE LOGITS
    })
    1.52
     famed
    1.45
    ?).
    1.44
     perenn
    1.40
    )?
    1.40
     fame
    1.38
    ��
    1.37
     respectively
    1.36
     Nanto
    1.27
     ousted
    1.27
    Activations Density 0.603%

    No Known Activations