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. 15027
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "that" followed by a verb in past tense or other information

    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
    513
    +0.13
    0.4%
    2019
    +0.10
    0.3%
    1023
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    513
    +0.13
    0.05
    1023
    +0.10
    0.06
    1350
    +0.10
    0.05
    Negative Logits
     lele
    -0.99
     siena
    -0.99
     ananas
    -0.96
     koz
    -0.96
     makro
    -0.95
     Meksi
    -0.92
     avto
    -0.90
     eki
    -0.90
     lampa
    -0.90
     adal
    -0.89
    POSITIVE LOGITS
     shouldn
    0.68
     resembles
    0.67
     resonates
    0.62
     might
    0.62
     involves
    0.61
     requires
    0.61
     could
    0.61
     deserves
    0.61
     hasn
    0.61
     ressemble
    0.59
    Activations Density 0.210%

    No Known Activations