© 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. 7470
    Prev
    Next
    INDEX
    Explanations

    sentences related to financial issues and business decisions

    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
    1535
    +0.17
    0.5%
    2034
    +0.16
    0.5%
    382
    +0.15
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.17
    0.10
    1535
    +0.16
    0.07
    1021
    +0.15
    0.08
    Negative Logits
     gsx
    -1.03
     lamborghini
    -1.03
     isuzu
    -0.97
     chrysler
    -0.97
     husqvarna
    -0.97
     ktm
    -0.94
     kawasaki
    -0.93
     vespa
    -0.91
     lexus
    -0.91
     mondeo
    -0.90
    POSITIVE LOGITS
     Also
    0.70
     However
    0.67
     But
    0.67
     Hence
    0.64
     Therefore
    0.61
     Plus
    0.60
    Also
    0.60
     Additionally
    0.59
     Thus
    0.58
    However
    0.58
    Activations Density 0.594%

    No Known Activations