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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 7546
    Prev
    Next
    INDEX
    Explanations

    phrases indicating approaches or requests for assistance or collaboration

    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
    2:0.08
    3:0.07
    4:0.11
    5:0.02
    6:0.02
    7:0.43
    8:0.02
    9:0.03
    10:0.07
    11:0.08
    Negative Logits
    fact
    -1.61
    installed
    -1.58
     accumulated
    -1.53
    %).
    -1.51
    ankind
    -1.51
     belts
    -1.47
    anty
    -1.45
     depleted
    -1.44
    variable
    -1.44
    apsed
    -1.41
    POSITIVE LOGITS
     solicit
    1.84
     CLIENT
    1.62
     solicitation
    1.58
     ask
    1.57
    WARD
    1.56
     questions
    1.54
    ventus
    1.53
     enqu
    1.51
     QUEST
    1.51
    pport
    1.51
    Activations Density 0.015%

    No Known Activations