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. 400
    Prev
    Next
    INDEX
    Explanations

    references to business activities such as company announcements, funding rounds, and new headquarters openings

    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
    1177
    +0.11
    0.3%
    50
    +0.11
    0.3%
    1919
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.11
    0.09
    1919
    +0.11
    0.07
    862
    +0.10
    0.04
    Negative Logits
     Février
    -1.34
     Décembre
    -1.24
     Septembre
    -1.22
     Juillet
    -1.19
     Octobre
    -1.10
     noël
    -1.05
     répon
    -1.04
     chèvre
    -1.01
     trouva
    -1.00
     Novembre
    -0.99
    POSITIVE LOGITS
     announced
    0.85
     finally
    0.77
     announces
    0.74
     reportedly
    0.73
     continues
    0.73
     postponed
    0.69
     underwent
    0.69
     has
    0.69
     unveiled
    0.68
     unexpectedly
    0.68
    Activations Density 0.637%

    No Known Activations