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. 862
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "on."

    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
    +0.34
    1.6%
    1828
    +0.14
    0.7%
    2011
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1828
    +0.34
    0.10
    2011
    +0.14
    0.08
    31
    +0.14
    0.06
    Negative Logits
    <bos>
    -2.48
    ⓧ
    -0.97
    <?
    -0.71
    /**
    -0.67
    uxxxx
    -0.58
     viewWillAppear
    -0.58
    RegressionTest
    -0.58
     get
    -0.57
     awakeFromNib
    -0.57
    ViewFeatures
    -0.57
    POSITIVE LOGITS
     maneu
    1.45
     accla
    1.39
     Keny
    1.31
     Juf
    1.28
     délib
    1.25
     Ferdin
    1.24
     épu
    1.21
     soulign
    1.20
     habile
    1.20
     véhic
    1.19
    Activations Density 0.203%

    No Known Activations