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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 44328
    Prev
    Next
    INDEX
    Explanations

    numerical references or data points related to performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.13
    1:0.08
    2:0.09
    3:0.06
    4:0.08
    5:0.09
    6:0.07
    7:0.05
    8:0.09
    9:0.07
    10:0.07
    11:0.07
    Negative Logits
    iannopoulos
    -1.93
    APTER
    -1.73
    ichick
    -1.56
    �
    -1.53
    ritch
    -1.52
    uctive
    -1.52
     Disneyland
    -1.49
    estern
    -1.44
    EngineDebug
    -1.43
     2020
    -1.42
    POSITIVE LOGITS
     Cly
    1.68
    bah
    1.60
    Issue
    1.49
     allot
    1.47
     piety
    1.46
    shr
    1.43
    basic
    1.42
    notice
    1.42
    holding
    1.42
    vernment
    1.39
    Activations Density 0.000%

    No Known Activations