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. 1226
    Prev
    Next
    INDEX
    Explanations

    terms related to social justice and activism

    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
    +0.20
    0.8%
    1870
    +0.17
    0.6%
    332
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.20
    0.07
    1870
    +0.17
    0.05
    1992
    +0.09
    0.06
    Negative Logits
    <bos>
    -2.58
    /**
    -0.82
     springfox
    -0.73
    <?
    -0.72
    /*
    -0.71
     mobilize
    -0.66
    EndProject
    -0.63
    amaño
    -0.61
     stabilize
    -0.60
     unify
    -0.59
    POSITIVE LOGITS
     quoique
    1.11
     soulign
    1.03
     pylab
    0.93
     embodi
    0.89
     devenus
    0.88
     véhic
    0.88
     chrysler
    0.86
     riva
    0.86
     affor
    0.85
     wikihow
    0.85
    Activations Density 0.464%

    No Known Activations