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. 9142
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming and variables

    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
    0:0.05
    1:0.06
    2:0.20
    3:0.03
    4:0.03
    5:0.03
    6:0.04
    7:0.04
    8:0.03
    9:0.04
    10:0.35
    11:0.03
    Negative Logits
    axis
    -2.46
    ihad
    -2.38
    671
    -2.37
    iang
    -2.37
    hen
    -2.34
    ß
    -2.25
    agos
    -2.25
    idth
    -2.25
    igon
    -2.24
    ITIES
    -2.23
    POSITIVE LOGITS
     Rec
    4.07
    rec
    3.85
     rec
    3.43
     REC
    3.40
    Rec
    3.36
    REC
    3.10
     Ret
    3.05
     Proc
    2.62
     recy
    2.59
    Ret
    2.58
    Activations Density 0.000%

    No Known Activations