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. 3-ATT-KK
    6. 10488
    Prev
    Next
    INDEX
    Explanations

    strong expressions of certainty or statements regarding the truthfulness of claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.04
    2:0.07
    3:0.06
    4:0.01
    5:0.05
    6:0.12
    7:0.18
    8:0.09
    9:0.04
    10:0.08
    11:0.19
    Negative Logits
    ivas
    -1.44
    iva
    -1.11
    asio
    -1.10
    essage
    -1.10
    cellence
    -1.09
    ordes
    -1.09
    ーン
    -1.08
    yssey
    -1.08
    ascade
    -1.06
    vg
    -1.06
    POSITIVE LOGITS
     peripher
    1.31
     annex
    1.17
     impair
    1.16
     embargo
    1.10
     cannabin
    1.09
     tant
    1.09
     packaging
    1.07
     except
    1.07
    etheless
    1.07
    cot
    1.06
    Activations Density 0.026%

    No Known Activations