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. 15790
    Prev
    Next
    INDEX
    Explanations

    and extract information related to signal processing and technical procedures

    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
    453
    +0.24
    0.7%
    1343
    +0.22
    0.6%
    2019
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.24
    0.06
    1343
    +0.22
    0.04
    184
    +0.11
    0.02
    Negative Logits
     reluct
    -2.58
     volunte
    -2.51
     Confu
    -2.36
     fta
    -2.35
     disagre
    -2.33
     Juf
    -2.33
     increa
    -2.30
     shenan
    -2.30
     accla
    -2.29
     philanth
    -2.29
    POSITIVE LOGITS
    Obrázky
    0.71
        
    0.71
      
    0.69
    span
    0.69
    	
    0.69
    ხ
    0.69
         
    0.68
           
    0.67
    ্ব
    0.67
    Bibliografía
    0.67
    Activations Density 0.198%

    No Known Activations