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. 15718
    Prev
    Next
    INDEX
    Explanations

    adjectives describing the size or complexity of things

    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
    284
    +0.08
    0.2%
    1216
    +0.07
    0.2%
    674
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.08
    0.04
    384
    +0.07
    0.03
    1216
    +0.07
    0.03
    Negative Logits
    /***
    
    -0.57
     fasc
    -0.56
     incont
    -0.56
     Settembre
    -0.56
     incess
    -0.56
    expandindo
    -0.56
     spacy
    -0.55
     parteci
    -0.55
     sensibili
    -0.55
     Prova
    -0.55
    POSITIVE LOGITS
     înc
    0.87
     that
    0.62
     ujedno
    0.58
     OSError
    0.55
     it
    0.55
    roidery
    0.53
     so
    0.52
     nutella
    0.51
    ATEGORY
    0.51
    that
    0.51
    Activations Density 0.152%

    No Known Activations