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. 852
    Prev
    Next
    INDEX
    Explanations

    expressions of personal enthusiasm or preference

    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
    +0.26
    0.9%
    605
    +0.10
    0.4%
    658
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1470
    +0.26
    0.03
    605
    +0.10
    0.01
    1773
    +0.08
    0.03
    Negative Logits
    <bos>
    -1.82
    protected
    -0.68
    /**
    -0.67
    var
    -0.64
     became
    -0.64
     appeared
    -0.63
     become
    -0.63
    enumerate
    -0.63
    public
    -0.62
     becomes
    -0.62
    POSITIVE LOGITS
     Minang
    1.38
     increa
    1.36
     reluct
    1.35
     impra
    1.31
     cytoplas
    1.30
     swarovski
    1.28
     affor
    1.27
     quoique
    1.27
     disreg
    1.25
     maneu
    1.25
    Activations Density 0.291%

    No Known Activations