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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 196
    Prev
    Next
    INDEX
    Explanations

    detailed economic and market analysis related to investment decision-making

    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
    +0.26
    1.1%
    2019
    +0.13
    0.5%
    341
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    623
    +0.26
    0.06
    438
    +0.13
    0.06
    2019
    +0.06
    0.06
    Negative Logits
    <bos>
    -2.03
    ⓧ
    -0.89
    /**
    -0.80
    <?
    -0.77
     ratify
    -0.74
    <?
    
    -0.74
     modernize
    -0.71
    
    
    -0.71
     inaugurate
    -0.69
     endow
    -0.69
    POSITIVE LOGITS
     Jusqu
    0.79
     fabriqué
    0.79
     véhic
    0.77
     rafra
    0.76
     considér
    0.76
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.75
     proprement
    0.74
     pleins
    0.74
    dison
    0.73
     épu
    0.73
    Activations Density 0.155%

    No Known Activations