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. 13578
    Prev
    Next
    INDEX
    Explanations

    Specific currency amounts in Swedish krona and email addresses

    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
    1343
    +0.17
    0.5%
    184
    +0.15
    0.5%
    1177
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.17
    0.02
    1654
    +0.15
    0.03
    1343
    +0.12
    0.04
    Negative Logits
    ValueGenerated
    -1.05
     &___
    -0.92
     AssemblyCompany
    -0.91
     autorytatywna
    -0.91
     EconPapers
    -0.89
    SharedDtor
    -0.89
    fromnode
    -0.89
    PreferredItem
    -0.89
    Personensuche
    -0.89
    oredCriteria
    -0.89
    POSITIVE LOGITS
     ?...
    2.15
     !...
    2.01
     fuf
    1.98
     unden
    1.96
     squa
    1.96
     inev
    1.95
     increa
    1.94
     fta
    1.93
     desir
    1.91
     uniqu
    1.90
    Activations Density 0.134%

    No Known Activations