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. 15615
    Prev
    Next
    INDEX
    Explanations

    phrases related to urban environments and activities, particularly focusing on urban farming

    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
    1870
    +0.17
    0.6%
    314
    +0.13
    0.5%
    577
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.17
    0.02
    765
    +0.13
    0.02
    437
    +0.12
    0.02
    Negative Logits
     michelle
    -0.53
     alaska
    -0.51
     timberland
    -0.49
     unve
    -0.49
     RAILROAD
    -0.47
     philippines
    -0.47
    amélioration
    -0.47
     arizona
    -0.47
     tár
    -0.46
     sandra
    -0.45
    POSITIVE LOGITS
     urban
    1.25
    Urban
    1.21
     Urban
    1.16
    urban
    1.16
    URBAN
    1.12
     URBAN
    1.05
     urbana
    0.99
     Urbano
    0.98
     urb
    0.91
     urbano
    0.91
    Activations Density 0.056%

    No Known Activations