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. 10-RES-JB
    6. 1045
    Prev
    Next
    INDEX
    Explanations

    evaluations of product value based on price and performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.25
    1.0%
    876
    +0.22
    0.9%
    1385
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.25
    -0.03
    1403
    +0.22
    0.02
    1042
    +0.14
    0.06
    Negative Logits
    <bos>
    -2.90
    
    
    -0.92
     esquecer
    -0.89
    },{
    
    -0.81
    /**
    -0.80
    <?
    -0.80
    ⓧ
    -0.78
     assistir
    -0.78
     aceitar
    -0.77
     puder
    -0.76
    POSITIVE LOGITS
     ecru
    1.51
     tupperware
    1.42
     swarovski
    1.37
     considér
    1.24
     tricot
    1.20
     hairc
    1.17
     vété
    1.15
     embodi
    1.14
     taupe
    1.10
     malheureux
    1.08
    Activations Density 1.391%

    No Known Activations