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. 7-ATT-KK
    6. 8964
    Prev
    Next
    INDEX
    Explanations

    references to quantities and measures related to wood or timber

    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
    0:0.36
    1:0.04
    2:0.01
    3:0.06
    4:0.08
    5:0.08
    6:0.06
    7:0.03
    8:0.08
    9:0.10
    10:0.02
    11:0.03
    Negative Logits
    oward
    -1.66
    outheastern
    -1.58
     CTR
    -1.57
    Interstitial
    -1.47
     bronze
    -1.43
     varying
    -1.38
    undreds
    -1.37
    liest
    -1.36
    doi
    -1.35
     predominant
    -1.34
    POSITIVE LOGITS
     ado
    1.80
    icion
    1.75
    kees
    1.72
    Reviewer
    1.71
     disclaim
    1.57
     lawy
    1.56
    "!
    1.53
    "],
    1.53
    tics
    1.50
    "},
    1.49
    Activations Density 0.000%

    No Known Activations