© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 41
    Prev
    Next
    INDEX
    Explanations

    terms related to transparency and openness

    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
    +0.22
    1.2%
    1262
    +0.13
    0.7%
    1127
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1127
    +0.22
    0.02
    1233
    +0.13
    0.02
    757
    +0.13
    0.02
    Negative Logits
    <bos>
    -2.50
     intersper
    -1.39
    ⓧ
    -1.36
    
    -1.21
    /***
    -1.19
    <?
    -1.15
    /**
    -1.10
    <?
    -1.05
     encomp
    -1.02
     amass
    -1.01
    POSITIVE LOGITS
     transparency
    1.30
     transparent
    1.13
    Transparency
    1.11
     Transparency
    1.11
    transparency
    1.07
    Transparent
    1.05
    transparent
    1.03
     Transparent
    1.01
     transparente
    0.98
     transparentes
    0.96
    Activations Density 0.026%

    No Known Activations