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. 1462
    Prev
    Next
    INDEX
    Explanations

    positive mentions and support from community-related contexts

    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
    764
    +0.11
    0.3%
    478
    +0.09
    0.3%
    227
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.11
    0.10
    227
    +0.09
    0.08
    1097
    +0.09
    0.07
    Negative Logits
    algunos
    -0.58
     Çünkü
    -0.55
     despotism
    -0.54
     برابوك
    -0.53
     repug
    -0.52
    Przyp
    -0.51
    žnost
    -0.51
     Dzięki
    -0.51
     lenger
    -0.50
     Tampoco
    -0.49
    POSITIVE LOGITS
    <eos>
    0.78
     abbra
    0.72
     profi
    0.70
     anonyme
    0.67
    WebElementEntity
    0.62
     emi
    0.61
     mef
    0.61
     sark
    0.61
     tutt
    0.60
     évé
    0.58
    Activations Density 0.626%

    No Known Activations