© 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. 13451
    Prev
    Next
    INDEX
    Explanations

    phrases related to boosting economic or financial situations

    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
    1145
    +0.13
    0.5%
    1416
    +0.13
    0.5%
    890
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    890
    +0.13
    0.03
    1145
    +0.13
    0.03
    1416
    +0.12
    0.02
    Negative Logits
     Tef
    -0.70
     intermitt
    -0.69
     compréhen
    -0.67
     lidl
    -0.66
     michelin
    -0.66
     volunte
    -0.66
     Riti
    -0.66
     embra
    -0.64
     erad
    -0.64
     cabrio
    -0.62
    POSITIVE LOGITS
     boost
    1.37
    boost
    1.25
     boosting
    1.22
     boosts
    1.17
     boosted
    1.12
     Boost
    1.10
    Boost
    1.03
     booster
    0.94
    BOOST
    0.90
     boosters
    0.90
    Activations Density 0.094%

    No Known Activations