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. 9100
    Prev
    Next
    INDEX
    Explanations

    the command or statement to "go."

    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
    1:0.05
    2:0.03
    3:0.13
    4:0.06
    5:0.09
    6:0.07
    7:0.05
    8:0.23
    9:0.08
    10:0.05
    11:0.04
    Negative Logits
    ufact
    -2.14
    raft
    -2.06
    gery
    -2.00
     Skinner
    -1.88
     Obj
    -1.82
    ienne
    -1.77
    mop
    -1.75
     Chop
    -1.71
    anguage
    -1.71
    ows
    -1.69
    POSITIVE LOGITS
    Interstitial
    1.99
    CONCLUS
    1.86
     PLUS
    1.86
     Meter
    1.81
     desper
    1.80
     Leilan
    1.79
     +++
    1.77
     />
    1.76
     culmin
    1.76
    だ
    1.73
    Activations Density 0.000%

    No Known Activations