© 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. 537
    Prev
    Next
    INDEX
    Explanations

    financial terms and numbers related to government spending

    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
    1253
    +0.14
    0.4%
    674
    +0.11
    0.3%
    1013
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2043
    +0.14
    0.04
    609
    +0.11
    0.04
    1553
    +0.10
    0.05
    Negative Logits
     meis
    -1.05
     juf
    -0.95
     wien
    -0.88
     „,
    -0.88
     inder
    -0.86
     ftu
    -0.85
     gij
    -0.82
     myn
    -0.82
     aen
    -0.80
     emphat
    -0.79
    POSITIVE LOGITS
     annually
    0.64
     savings
    0.57
     annual
    0.53
    savings
    0.53
     billions
    0.51
    bosis
    0.50
     lost
    0.48
     losses
    0.47
     billion
    0.47
    chequer
    0.47
    Activations Density 0.307%

    No Known Activations