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. 898
    Prev
    Next
    INDEX
    Explanations

    references to convenience and ease of use in products or technologies

    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
    +0.30
    1.1%
    876
    +0.15
    0.6%
    1013
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.30
    -0.01
    282
    +0.15
    0.04
    1385
    +0.10
    0.06
    Negative Logits
    <bos>
    -2.81
    IEnumerator
    -0.71
    Etimología
    -0.69
    HasIndex
    -0.68
    lateinit
    -0.65
    /***
    
    -0.64
    HttpDelete
    -0.58
    Etimo
    -0.58
     inserir
    -0.57
    DebuggerStep
    -0.57
    POSITIVE LOGITS
     bandung
    1.62
     milano
    1.41
     swarovski
    1.38
     murano
    1.32
     ibiza
    1.25
     sentito
    1.24
     santiago
    1.23
     soggior
    1.22
     paradiso
    1.21
     leonardo
    1.20
    Activations Density 0.649%

    No Known Activations