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. 7203
    Prev
    Next
    INDEX
    Explanations

    terms related to free speech and its associated challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    0:0.03
    1:0.10
    2:0.03
    3:0.06
    4:0.04
    5:0.27
    6:0.04
    7:0.10
    8:0.06
    9:0.05
    10:0.11
    11:0.05
    Negative Logits
     (~
    -1.71
    gio
    -1.71
    neau
    -1.70
    DK
    -1.66
     Paso
    -1.57
    orf
    -1.56
    gins
    -1.54
    mega
    -1.54
    Prep
    -1.54
    mone
    -1.53
    POSITIVE LOGITS
    href
    2.05
     Eater
    1.76
     Expression
    1.73
    ignty
    1.73
     Voting
    1.71
     redes
    1.70
     Freedom
    1.68
     dissent
    1.68
    resp
    1.67
     Clause
    1.65
    Activations Density 0.001%

    No Known Activations