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. 1147
    Prev
    Next
    INDEX
    Explanations

    references to the Tor network and related projects

    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
    +0.15
    0.5%
    437
    +0.09
    0.4%
    198
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.15
    0.10
    304
    +0.09
    0.00
    1097
    +0.09
    0.08
    Negative Logits
    <bos>
    -2.37
    Sản
    -0.81
    Màu
    -0.79
     initComponents
    -0.77
    Asimismo
    -0.75
    RectangleBorder
    -0.72
     manage
    -0.72
    lasia
    -0.72
    Xuất
    -0.72
     PeEnEo
    -0.72
    POSITIVE LOGITS
     increa
    2.77
     impra
    2.66
     maneu
    2.60
     affor
    2.46
     accla
    2.46
     depic
    2.43
     squa
    2.42
     fortn
    2.41
     stockholm
    2.36
     madonna
    2.35
    Activations Density 0.657%

    No Known Activations