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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1574
    Prev
    Next
    INDEX
    Explanations

    names involving "Singh."

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1942
    +0.17
    0.7%
    597
    +0.15
    0.6%
    1872
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.17
    0.03
    1872
    +0.15
    0.02
    227
    +0.14
    0.03
    Negative Logits
     krishna
    -0.65
     sentito
    -0.61
     scopri
    -0.61
     aspetta
    -0.58
     dimenti
    -0.54
     lasciato
    -0.52
     dimentic
    -0.51
     trover
    -0.51
     raccont
    -0.50
     cammin
    -0.50
    POSITIVE LOGITS
     Singh
    1.15
    Singh
    1.09
     Sikh
    0.86
     SINGH
    0.75
     Sikhs
    0.74
     Şi
    0.70
     Sing
    0.68
     Singapur
    0.68
     Châ
    0.68
     Lég
    0.68
    Activations Density 0.117%

    No Known Activations