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. 6-RES-JB
    6. 146
    Prev
    Next
    INDEX
    Explanations

    terms related to activism, social movements, and significant social changes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.15
    0.9%
    2011
    +0.09
    0.5%
    783
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    869
    +0.15
    0.02
    783
    +0.09
    0.02
    241
    +0.09
    0.02
    Negative Logits
    <bos>
    -3.17
    ⓧ
    -0.87
    /***
    
    -0.84
    <?
    -0.82
    /**
    -0.74
    
    
    -0.73
    <?
    
    -0.73
     fend
    -0.72
    /*
    -0.66
     manage
    -0.66
    POSITIVE LOGITS
     jaya
    1.31
     lele
    1.30
     bandung
    1.26
     Minang
    1.25
     montagna
    1.24
     riva
    1.24
     jawa
    1.17
     soggior
    1.16
     véhic
    1.14
     vasi
    1.09
    Activations Density 0.100%

    No Known Activations