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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1175
    Prev
    Next
    INDEX
    Explanations

    modal verbs and references to legislative or governmental actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.40
    1.6%
    478
    +0.07
    0.3%
    1306
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.40
    0.08
    1948
    +0.07
    0.06
    791
    +0.06
    0.05
    Negative Logits
    <bos>
    -2.94
     endow
    -0.86
     intersper
    -0.80
    /***
    
    -0.75
     disbur
    -0.69
     personalise
    -0.67
     amass
    -0.67
     subdue
    -0.66
     banish
    -0.65
     renounce
    -0.65
    POSITIVE LOGITS
     Luglio
    0.90
     tramont
    0.90
     Minang
    0.86
     Palembang
    0.84
     Ottobre
    0.83
     sappi
    0.83
     Jambi
    0.82
     Muhamma
    0.80
     purtroppo
    0.79
     chiunque
    0.79
    Activations Density 0.772%

    No Known Activations