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. 1257
    Prev
    Next
    INDEX
    Explanations

    numerical statistics related to sports 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
    1.1%
    1967
    +0.13
    0.6%
    752
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1905
    +0.25
    0.08
    1804
    +0.13
    0.07
    453
    +0.13
    0.07
    Negative Logits
    <bos>
    -2.17
    ⓧ
    -1.07
    /**
    -0.90
     disarm
    -0.79
    
    
    -0.79
     gratify
    -0.78
    /*
    -0.76
     springfox
    -0.74
    ,
    -0.71
     effectually
    -0.70
    POSITIVE LOGITS
     incess
    1.32
     marte
    1.30
     Luglio
    1.24
     majest
    1.23
     tramont
    1.23
     apparti
    1.22
     Giugno
    1.22
     karton
    1.22
     sappi
    1.21
     monaster
    1.20
    Activations Density 0.349%

    No Known Activations