© 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. 13365
    Prev
    Next
    INDEX
    Explanations

    mentions related to financial terms and government expenses

    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
    168
    +0.12
    0.4%
    1557
    +0.11
    0.3%
    1870
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1557
    +0.12
    0.02
    168
    +0.11
    0.02
    1948
    +0.10
    0.02
    Negative Logits
     thut
    -0.64
     habet
    -0.62
     afp
    -0.61
     nomine
    -0.60
     fatis
    -0.60
     wien
    -0.59
     kram
    -0.57
     xxiv
    -0.57
     effe
    -0.56
     myn
    -0.56
    POSITIVE LOGITS
     taxpayers
    1.29
     taxpayer
    1.25
    payers
    0.84
     tax
    0.81
     Tax
    0.75
    payer
    0.74
     taxes
    0.71
     TAX
    0.69
    Tax
    0.67
     payers
    0.66
    Activations Density 0.047%

    No Known Activations