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. 908
    Prev
    Next
    INDEX
    Explanations

    HTML elements and their interactions with JavaScript in web development contexts

    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
    +0.29
    1.2%
    876
    +0.15
    0.6%
    678
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.29
    -0.01
    678
    +0.15
    0.06
    1699
    +0.15
    0.06
    Negative Logits
    <bos>
    -2.86
    ⓧ
    -1.27
    
    
    -1.04
    Vegeu
    -0.98
    Pró
    -0.95
    Rusia
    -0.95
     springfox
    -0.91
    <?
    -0.91
    /**
    -0.88
    <?
    
    -0.87
    POSITIVE LOGITS
     maroc
    1.37
     wien
    1.31
     milano
    1.21
     italia
    1.20
     amsterdam
    1.13
     OGS
    1.12
     jawa
    1.12
     gmbh
    1.11
    antastic
    1.09
     bandung
    1.09
    Activations Density 0.459%

    No Known Activations