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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 639
    Prev
    Next
    INDEX
    Explanations

    numerical data and performance metrics in a cycling context

    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
    2019
    +0.20
    0.9%
    1343
    +0.16
    0.7%
    50
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.20
    0.05
    906
    +0.16
    0.01
    304
    +0.15
    0.01
    Negative Logits
    <bos>
    -2.58
    ⓧ
    -1.38
    /**
    -1.19
     springfox
    -1.18
    <?
    -1.15
    
    
    -1.10
    /*
    -1.06
    новништво
    -0.82
    <?
    
    -0.81
    /*++
    -0.80
    POSITIVE LOGITS
     accla
    1.48
     maneu
    1.41
     affor
    1.40
     intrigu
    1.32
     depic
    1.31
     emphat
    1.29
     Juf
    1.28
     increa
    1.27
     inev
    1.26
     lele
    1.25
    Activations Density 0.104%

    No Known Activations