© 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. 12184
    Prev
    Next
    INDEX
    Explanations

    references to time, history, and the concept of past, present, and future

    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
    1291
    +0.07
    0.2%
    89
    +0.07
    0.2%
    216
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    134
    +0.07
    0.03
    1232
    +0.07
    0.02
    1030
    +0.07
    0.02
    Negative Logits
     increa
    -0.92
     disagre
    -0.92
     reluct
    -0.90
     friable
    -0.88
     unden
    -0.87
     affor
    -0.87
     unwarran
    -0.86
     suscep
    -0.85
     impra
    -0.85
     michelin
    -0.84
    POSITIVE LOGITS
     future
    1.10
    future
    0.99
     current
    0.97
    Future
    0.92
    current
    0.87
     Future
    0.84
     futuro
    0.83
     present
    0.80
     Current
    0.80
     futures
    0.80
    Activations Density 0.352%

    No Known Activations