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. 9131
    Prev
    Next
    INDEX
    Explanations

    topics related to real objects or tangible items, especially in contexts highlighting their value or significance

    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
    0:0.07
    1:0.04
    2:0.02
    3:0.12
    4:0.04
    5:0.20
    6:0.05
    7:0.03
    8:0.11
    9:0.24
    10:0.02
    11:0.02
    Negative Logits
    76561
    -2.58
    }}}
    -2.35
    MpServer
    -2.33
     goose
    -2.31
    FTWARE
    -2.13
     Fenrir
    -2.12
    BuyableInstoreAndOnline
    -2.10
    SourceFile
    -2.09
    _-_
    -2.08
    ^^^^
    -2.06
    POSITIVE LOGITS
     devoid
    2.68
     esche
    2.53
     avoids
    2.50
     unaffected
    2.46
     smoothly
    2.39
     unlike
    2.38
    manent
    2.33
     retains
    2.32
     Instead
    2.32
     opted
    2.29
    Activations Density 0.036%

    No Known Activations