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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15885
    Prev
    Next
    INDEX
    Explanations

    subjects related to protests, strikes, and demonstrations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1343
    +0.35
    1.2%
    394
    +0.18
    0.6%
    227
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.35
    0.06
    453
    +0.18
    0.05
    2002
    +0.14
    0.03
    Negative Logits
     betweenstory
    -0.91
     виправивши
    -0.82
    Autoritní
    -0.82
    <bos>
    -0.78
     propOrder
    -0.75
    Datuak
    -0.71
     >=",
    -0.69
     سكانية
    -0.66
    oredCriteria
    -0.65
    fromnode
    -0.65
    POSITIVE LOGITS
     mef
    1.23
     ordina
    1.18
     nomine
    1.16
     inder
    1.15
     meis
    1.15
     socie
    1.14
     anton
    1.13
     dispen
    1.12
     §.
    1.12
     laun
    1.12
    Activations Density 0.200%

    No Known Activations