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. 1127
    Prev
    Next
    INDEX
    Explanations

    specific products or items for sale

    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
    +0.31
    1.4%
    198
    +0.18
    0.8%
    394
    +0.17
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.31
    0.10
    1265
    +0.18
    0.05
    382
    +0.17
    0.06
    Negative Logits
    <bos>
    -2.65
    ⓧ
    -0.96
    Geplaatst
    -0.90
    /**
    -0.87
    Referències
    -0.86
    contentLoaded
    -0.85
    ɵɵelement
    -0.84
    devServer
    -0.84
    HasIndex
    -0.83
    <?
    -0.82
    POSITIVE LOGITS
     increa
    1.96
     affor
    1.91
     maneu
    1.88
     reluct
    1.86
     impra
    1.81
     guarante
    1.77
     inev
    1.75
     accla
    1.71
     strick
    1.64
     disagre
    1.64
    Activations Density 1.533%

    No Known Activations