© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14748
    Prev
    Next
    INDEX
    Explanations

    contact information related to media outlets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.04
    2:0.06
    3:0.10
    4:0.18
    5:0.04
    6:0.13
    7:0.07
    8:0.11
    9:0.05
    10:0.06
    11:0.05
    Negative Logits
    glers
    -3.21
     barg
    -2.43
    naire
    -2.35
     franch
    -2.33
    steam
    -2.29
    xus
    -2.27
    acular
    -2.25
    _>
    -2.19
    ](
    -2.19
     zo
    -2.11
    POSITIVE LOGITS
     Errors
    2.29
     Gork
    2.24
     Citation
    2.23
     Bearing
    2.05
     errors
    2.02
    Reading
    2.01
     Editorial
    2.01
    ribe
    2.01
    critical
    2.00
    Error
    2.00
    Activations Density 0.003%

    No Known Activations