© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7222
    Prev
    Next
    INDEX
    Explanations

    references to newspapers and their related content

    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
    789
    +0.12
    0.4%
    479
    +0.11
    0.4%
    1870
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    789
    +0.12
    0.02
    136
    +0.11
    0.01
    783
    +0.11
    0.02
    Negative Logits
     Membre
    -0.65
     Directeur
    -0.65
     hek
    -0.62
     Docteur
    -0.61
     Wikisource
    -0.60
     keram
    -0.57
     vern
    -0.56
     pochette
    -0.56
     utop
    -0.55
     tille
    -0.55
    POSITIVE LOGITS
     newspaper
    1.28
     newspapers
    1.15
     Newspaper
    1.07
    newspaper
    1.01
     Newspapers
    0.97
    Newspaper
    0.96
     paper
    0.67
     papers
    0.65
     news
    0.62
    paper
    0.61
    Activations Density 0.062%

    No Known Activations