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. 5-ATT-KK
    6. 28139
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.14
    1:0.04
    2:0.10
    3:0.07
    4:0.05
    5:0.03
    6:0.15
    7:0.05
    8:0.08
    9:0.06
    10:0.10
    11:0.08
    Negative Logits
    irk
    -1.49
    hoe
    -1.47
    uay
    -1.47
    ht
    -1.44
    squ
    -1.39
    phe
    -1.35
    gged
    -1.33
    ymm
    -1.32
    abal
    -1.30
    saf
    -1.30
    POSITIVE LOGITS
    Interstitial
    1.59
    anwhile
    1.44
     Mania
    1.39
    pleting
    1.36
     Pengu
    1.34
    PDATE
    1.31
     TTL
    1.27
     lasts
    1.26
     cryst
    1.25
     calendars
    1.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.