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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22275
    Prev
    Next
    INDEX
    Explanations

    terms associated with legality and compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.02
    2:0.41
    3:0.05
    4:0.12
    5:0.05
    6:0.02
    7:0.02
    8:0.06
    9:0.08
    10:0.05
    11:0.02
    Negative Logits
    linger
    -1.32
    urrencies
    -1.23
    aminer
    -1.20
    veland
    -1.16
     Doomsday
    -1.15
    wark
    -1.14
    minster
    -1.13
    opoulos
    -1.13
    kefeller
    -1.12
    aiden
    -1.10
    POSITIVE LOGITS
    cedented
    1.40
    akable
    1.33
    conn
    1.26
    orable
    1.25
    sembly
    1.19
     exha
    1.14
    CONT
    1.12
    widget
    1.11
    ciating
    1.10
     Indra
    1.10
    Activations Density 0.019%

    No Known Activations