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. 6146
    Prev
    Next
    INDEX
    Explanations

    "support" or "backing" associated with policies or decisions

    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
    0.9%
    605
    +0.10
    0.4%
    573
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    710
    +0.23
    0.04
    889
    +0.10
    0.04
    1892
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.79
    const
    -0.76
    
    
    -0.74
    public
    -0.71
     did
    -0.71
    /*
    -0.68
     have
    -0.68
    else
    -0.68
    		
    -0.68
     has
    -0.68
    POSITIVE LOGITS
     affor
    2.03
     impra
    1.98
     increa
    1.93
     stockholm
    1.91
     Juf
    1.87
     reluct
    1.82
     accla
    1.80
     fta
    1.80
     maneu
    1.79
     mef
    1.78
    Activations Density 0.718%

    No Known Activations