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

    Neuronpedia

    Jacobian LensNEW
    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. 5326
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial matters, specifically discussions around income disparities and economic 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
    897
    +0.12
    0.4%
    331
    +0.12
    0.4%
    11
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1052
    +0.12
    0.05
    376
    +0.12
    0.04
    331
    +0.10
    0.04
    Negative Logits
     المعيارى
    -0.51
    invokeLater
    -0.46
    즌
    -0.43
    br
    -0.43
    .*")]
    -0.43
    EQUAL
    -0.43
    N
    -0.42
    zarchiwizowane
    -0.42
    LabelTagHelper
    -0.41
    SharedDtor
    -0.41
    POSITIVE LOGITS
     dovr
    0.90
     broderie
    0.78
     maksi
    0.74
     affez
    0.71
     exé
    0.70
     carrefour
    0.70
     venuto
    0.69
     écart
    0.68
     évit
    0.68
     désert
    0.68
    Activations Density 0.138%

    No Known Activations