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. 1049
    Prev
    Next
    INDEX
    Explanations

    terms related to draft picks

    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
    1.3%
    1961
    +0.13
    0.7%
    1926
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1562
    +0.25
    0.03
    1872
    +0.13
    0.02
    1926
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.78
    JspWriter
    -0.71
    displayquote
    -0.70
    //{
    
    -0.64
    </tbody>
    -0.64
    setVerticalGroup
    -0.64
    //}
    
    -0.63
    public
    -0.62
    Portály
    -0.62
    GraphicsUnit
    -0.62
    POSITIVE LOGITS
     maneu
    1.76
     indestru
    1.60
     affor
    1.56
     increa
    1.55
     shenan
    1.52
     impra
    1.52
     accla
    1.51
     disagre
    1.49
     inev
    1.48
     unspeak
    1.47
    Activations Density 0.027%

    No Known Activations