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. 15559
    Prev
    Next
    INDEX
    Explanations

    locational information and infrastructure details related to urban development projects

    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
    964
    +0.16
    0.5%
    906
    +0.11
    0.3%
    1120
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    964
    +0.16
    0.04
    939
    +0.11
    0.04
    870
    +0.10
    0.03
    Negative Logits
     vogel
    -0.57
     niem
    -0.57
     eset
    -0.50
     cze
    -0.50
     heren
    -0.49
     câte
    -0.49
     ziem
    -0.49
     loggedIn
    -0.48
     userEmail
    -0.47
     przecież
    -0.47
    POSITIVE LOGITS
     Docteur
    1.05
     Chapitre
    0.92
     ladite
    0.91
     vété
    0.88
     hcm
    0.88
     Nguy
    0.86
     Bâ
    0.85
     thuy
    0.84
     Juf
    0.82
     ledit
    0.82
    Activations Density 0.147%

    No Known Activations