Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5596
    Prev
    Next
    INDEX
    Explanations

    phrases related to recognition and admiration, particularly in a community context

    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
    +0.18
    1.0%
    1065
    +0.13
    0.7%
    596
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1490
    +0.18
    0.03
    1065
    +0.13
    0.03
    501
    +0.10
    0.03
    Negative Logits
    <bos>
    -3.15
    
    
    -0.92
    ⓧ
    -0.91
    /***
    
    -0.77
    /**
    -0.72
    <?
    -0.71
    public
    -0.69
    Controllo
    -0.66
    HasColumnType
    -0.64
    		
    -0.62
    POSITIVE LOGITS
     maneu
    1.77
     impra
    1.54
     stockholm
    1.48
     Minang
    1.47
     increa
    1.42
     eiffel
    1.41
     wien
    1.40
     affor
    1.38
     shenan
    1.37
     sappi
    1.37
    Activations Density 0.098%

    No Known Activations