© 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 EvalsExportsinterp-engineNEWAPI 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. 4845
    Prev
    Next
    INDEX
    Explanations

    positive sentiments related to food and life

    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
    872
    +0.08
    0.2%
    594
    +0.07
    0.2%
    648
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1282
    +0.08
    0.03
    594
    +0.07
    0.04
    69
    +0.06
    0.01
    Negative Logits
     Strukt
    -0.79
     praktik
    -0.75
     haer
    -0.73
     Gorb
    -0.71
     territo
    -0.71
     Jär
    -0.71
    kiv
    -0.71
     Jä
    -0.70
     dépasse
    -0.70
     magis
    -0.70
    POSITIVE LOGITS
     suddenly
    0.74
     becomes
    0.72
     became
    0.65
     become
    0.65
     disappears
    0.64
     finally
    0.62
     now
    0.61
     disappeared
    0.61
     vanished
    0.55
    Może
    0.55
    Activations Density 0.420%

    No Known Activations