© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12620
    Prev
    Next
    INDEX
    Explanations

    references to economic crises or downturns, particularly the term 'Recession'

    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
    2034
    +0.10
    0.3%
    1499
    +0.09
    0.3%
    1438
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.10
    0.05
    914
    +0.09
    0.03
    1241
    +0.09
    0.04
    Negative Logits
     effe
    -1.65
     desir
    -1.65
     unden
    -1.59
     nutr
    -1.57
     oner
    -1.55
     wien
    -1.54
     secon
    -1.53
     compen
    -1.52
     embodi
    -1.51
     suscep
    -1.51
    POSITIVE LOGITS
     period
    0.88
     era
    0.71
     periods
    0.70
     recession
    0.70
     occurred
    0.64
     pandemic
    0.64
     years
    0.63
     crisis
    0.63
     started
    0.62
    period
    0.62
    Activations Density 0.233%

    No Known Activations