© 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. 3865
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic demand and market conditions

    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
    1491
    +0.13
    0.4%
    596
    +0.13
    0.4%
    732
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1052
    +0.13
    0.03
    1708
    +0.13
    0.02
    1491
    +0.12
    0.02
    Negative Logits
     Verk
    -0.57
     Peker
    -0.52
     ideolog
    -0.52
     Mühl
    -0.51
     Böh
    -0.50
     Somal
    -0.49
     Malte
    -0.48
     Guten
    -0.47
     Floren
    -0.47
     verhe
    -0.46
    POSITIVE LOGITS
     demand
    1.30
     Demand
    1.28
    Demand
    1.28
    demand
    1.27
     DEMAND
    1.11
     demands
    1.11
     Demands
    1.01
     demanded
    0.92
     demanda
    0.84
     demanding
    0.83
    Activations Density 0.048%

    No Known Activations