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. 5405
    Prev
    Next
    INDEX
    Explanations

    phrases related to market statistics and analysis

    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
    +0.21
    1.3%
    1870
    +0.13
    0.9%
    1271
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1271
    +0.21
    0.04
    555
    +0.13
    0.04
    1026
    +0.12
    0.04
    Negative Logits
    <bos>
    -3.31
    ⓧ
    -0.87
    /***
    
    -0.72
    <?
    -0.70
    /*++
    -0.69
    
    
    -0.69
     mobilize
    -0.68
    /*
    -0.67
    <?
    
    -0.65
     evacuate
    -0.65
    POSITIVE LOGITS
     maneu
    1.25
     unlaw
    1.20
     quoique
    1.18
     embodi
    1.18
     hairc
    1.16
     Intere
    1.15
     Minang
    1.15
     Keny
    1.13
     pleins
    1.12
     Khart
    1.12
    Activations Density 0.077%

    No Known Activations