© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2789
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to political sentiments and opinions

    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
    1.0%
    964
    +0.09
    0.3%
    1919
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.29
    0.13
    2006
    +0.09
    0.07
    1510
    +0.08
    0.05
    Negative Logits
    <bos>
    -2.11
     intersper
    -1.32
    /***
    -0.92
     encomp
    -0.91
     endow
    -0.87
    <?
    -0.85
     trouva
    -0.85
     amass
    -0.84
     gratify
    -0.81
    Xoxo
    -0.79
    POSITIVE LOGITS
    SneakyThrows
    0.73
    bufio
    0.63
     condicionado
    0.63
    thalene
    0.61
    paraíso
    0.60
    abancı
    0.60
     avut
    0.60
    SBATCH
    0.60
    Dacă
    0.59
     signora
    0.58
    Activations Density 1.053%

    No Known Activations