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. 732
    Prev
    Next
    INDEX
    Explanations

    web content-related elements and interaction options, such as comments, replies, and engagement prompts

    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
    +0.23
    1.1%
    2019
    +0.14
    0.6%
    1343
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.23
    0.15
    924
    +0.14
    0.15
    1445
    +0.07
    0.14
    Negative Logits
    <bos>
    -3.28
    ⓧ
    -1.13
    /**
    -0.97
    <?
    -0.92
    
    
    -0.89
    /***
    
    -0.81
     ratify
    -0.70
     springfox
    -0.70
    /*
    -0.68
     shivered
    -0.67
    POSITIVE LOGITS
     véhic
    0.98
     pleins
    0.86
     milano
    0.86
     marseille
    0.83
     bandung
    0.83
     maroc
    0.82
     expériment
    0.81
     Luglio
    0.79
     multicolore
    0.78
     soulign
    0.78
    Activations Density 1.827%

    No Known Activations